© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 121836
    Prev
    Next
    INDEX
    Explanations

    ancient, desire, my boat

    np_acts-logits-general · gemini-2.5-flash-lite

    racism, transphobia, wandering, legacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     digitalen
    0.46
     الالكتر
    0.45
     digitales
    0.44
    ,
    0.43
    );
    0.43
     whatever
    0.43
    /
    0.43
     cualquiera
    0.41
    ،
    0.41
    ፣
    0.41
    POSITIVE LOGITS
     amiss
    0.48
     최초
    0.48
    ುವ
    0.47
    ちなみに
    0.47
    ้องกัน
    0.46
    ότερα
    0.45
     প্রাচীন
    0.45
     શોધ
    0.45
     ಮೊದಲ
    0.44
     చరిత్ర
    0.44
    Activations Density 0.001%

    No Known Activations