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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2184
    Prev
    Next
    INDEX
    Explanations

    programming prompts

    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
    هران
    -0.82
     bahaya
    -0.77
    冒
    -0.75
    ISING
    -0.74
     nôtre
    -0.73
    zungen
    -0.71
    波动
    -0.71
    畢
    -0.69
    idere
    -0.69
    ISY
    -0.68
    POSITIVE LOGITS
     into
    0.78
    atürk
    0.78
    )}-
    0.77
     away
    0.75
    diyesi
    0.75
    uhnya
    0.75
    アニ
    0.75
    +#+#
    0.74
     overseas
    0.74
    each
    0.74
    Activations Density 0.002%

    No Known Activations