© 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. 78038
    Prev
    Next
    INDEX
    Explanations

    to come or to be

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     to
    -1.98
    ማ
    -0.79
     TO
    -0.79
    lote
    -0.77
     stepped
    -0.77
     To
    -0.76
    to
    -0.75
    combat
    -0.73
     ブーツ
    -0.73
    goes
    -0.69
    POSITIVE LOGITS
     come
    3.53
    Come
    2.72
     Come
    2.63
     comes
    2.58
    come
    2.27
    來
    2.20
     came
    2.17
     datang
    2.16
     COME
    2.02
    COME
    1.98
    Activations Density 0.008%

    No Known Activations