© 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. 73760
    Prev
    Next
    INDEX
    Explanations

    bank names and affiliates

    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
    勿論
    -2.61
     extrêmement
    -2.55
    在自己
    -2.53
    未だ
    -2.41
    ほんとに
    -2.36
    ほんと
    -2.28
    めちゃくちゃ
    -2.23
    
    -2.23
    なかな
    -2.23
    焢
    -2.22
    POSITIVE LOGITS
    c
    3.44
    <td>
    2.88
    {
    2.78
    _{
    2.66
    ৄ
    2.58
    le
    2.58
    '));
    2.55
    p
    2.48
    ቍ
    2.38
    }(
    2.33
    Activations Density 0.006%

    No Known Activations