© 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. 137920
    Prev
    Next
    INDEX
    Explanations

    foreign languages and unique words

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

    pose several challenges

    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
     spore
    0.45
     basis
    0.44
    :"+
    0.43
     endregion
    0.42
     중요
    0.41
    zetten
    0.41
     메
    0.41
     ме
    0.41
    ㅡ
    0.40
     ತ
    0.40
    POSITIVE LOGITS
     ederim
    0.42
    Бе
    0.42
     Malam
    0.41
     Looking
    0.41
    ิ
    0.41
    商品は
    0.41
    გუფი
    0.41
     Mallory
    0.41
    سین
    0.40
     হাউস
    0.40
    Activations Density 0.000%

    No Known Activations