© 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. 34-GEMMASCOPE-RES-131K
    7. 78602
    Prev
    Next
    INDEX
    Explanations

    offered, presented, provided

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

    The neuron fires strongly on sentence-boundary punctuation (especially periods and commas) and on linking verbs like “is” in formal technical or product‐specification 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_34/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
     récente
    -1.03
    washingtonpost
    -0.86
    endaftaran
    -0.84
     семье
    -0.82
     muñecas
    -0.82
    ஊ
    -0.80
    OrderDetails
    -0.79
    现在
    -0.77
     것이다
    -0.77
     so
    -0.77
    POSITIVE LOGITS
     offered
    1.32
     Offered
    1.02
     offerte
    1.00
     proposed
    0.96
     presented
    0.94
     provided
    0.90
     brut
    0.89
    Offered
    0.88
     delivered
    0.88
    sub
    0.86
    Activations Density 0.008%

    No Known Activations