© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14037
    Prev
    Next
    INDEX
    Explanations

    organic acid names

    np_acts-logits-general · gemini-2.5-flash-lite

    chemical names and compounds ending with "ic acid" or chemical terminology related to acids.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is keyed to detect numerical measurement tokens—especially decimal or other numeric values—in scientific text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ༷
    -1.79
    ⤦
    -1.78
     merve
    -1.74
     desafio
    -1.73
    ༔
    -1.73
    瘆
    -1.72
     fisk
    -1.71
    𓐍
    -1.68
     fokus
    -1.66
    НОГО
    -1.65
    POSITIVE LOGITS
    such
    1.90
     знает
    1.87
     or
    1.83
    }
    1.71
     as
    1.66
     to
    1.66
     from
    1.65
     observación
    1.56
     ausdrück
    1.55
     seperti
    1.54
    Activations Density 0.085%

    No Known Activations