© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13683
    Prev
    Next
    INDEX
    Explanations

    words or non-English phrases

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

    The neuron fires on proper‐noun and entity tokens (e.g. organization names, titles, technical terms, person names, etc.).

    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
    see
    -1.05
     here
    -1.02
     zelfs
    -0.94
     allí
    -0.94
    できません
    -0.94
    しなかった
    -0.93
    𝕠
    -0.92
    ︲
    -0.92
    team
    -0.92
     which
    -0.91
    POSITIVE LOGITS
     sartén
    1.13
    agissait
    1.07
    ávajú
    1.06
    المل
    1.06
     accompagner
    1.04
    }
    1.03
    ými
    1.02
    oczes
    1.00
    ḿ
    0.99
    steak
    0.98
    Activations Density 0.775%

    No Known Activations