© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 52263
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    * against dangerous commentary

    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
     כי
    0.47
     i
    0.46
     오류
    0.46
     divisor
    0.45
     子供
    0.44
     sieve
    0.44
     CompoundButton
    0.44
     setResult
    0.43
     처
    0.42
     Brady
    0.42
    POSITIVE LOGITS
    و
    0.71
    нон
    0.58
    на
    0.55
    ющему
    0.54
    ز
    0.53
    ا
    0.52
    либ
    0.52
    ون
    0.51
    घव
    0.50
    ו
    0.50
    Activations Density 0.000%

    No Known Activations