© 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. 210960
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and advice

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

    deserve care and respect

    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
    ک
    0.53
    不少
    0.50
     sacro
    0.50
    ଞ
    0.47
     sebanyak
    0.47
    קו
    0.47
    𝗴
    0.47
    Klik
    0.46
    뽑
    0.46
    लाल
    0.46
    POSITIVE LOGITS
    ेच्छा
    0.46
     }-\
    0.43
     संघा
    0.43
     мне
    0.42
    ija
    0.41
     تبقى
    0.41
    //!
    0.41
     Halloween
    0.40
     civilization
    0.40
    жаем
    0.40
    Activations Density 0.000%

    No Known Activations