© 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. 113164
    Prev
    Next
    INDEX
    Explanations

    marked changes or qualities

    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_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
    粜
    -2.11
    ༷
    -2.11
    嵎
    -1.95
    opies
    -1.89
    忘記
    -1.88
    zied
    -1.88
    一点点
    -1.88
    それとも
    -1.84
     deviennent
    -1.83
    尨
    -1.83
    POSITIVE LOGITS
     and
    2.70
    </td>
    2.17
     if
    2.14
     This
    2.13
    N
    1.88
     at
    1.84
    1.78
     continue
    1.74
    scsi
    1.73
    他
    1.73
    Activations Density 0.053%

    No Known Activations