© 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. 128375
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    ).
    -2.72
    ↵↵
    -2.69
    </strong>
    -2.50
     «
    -2.50
     it
    -2.48
     and
    -2.45
    </em>
    -2.34
    ある
    -2.22
     –
    -2.20
    providedIn
    -2.20
    POSITIVE LOGITS
    いろいろな
    2.88
    訫
    2.84
    嫱
    2.83
    菔
    2.81
    うーん
    2.73
    龶
    2.69
    慇
    2.67
    𖧵
    2.66
    衚
    2.64
    {
    2.59
    Activations Density 0.005%

    No Known Activations