© 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. 190118
    Prev
    Next
    INDEX
    Explanations

    percentages and numbers

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

    numbers and percentages around them

    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
    反
    0.40
     использовать
    0.40
    rectionType
    0.38
    깐
    0.38
     反
    0.37
     स्टैंड
    0.37
    厳
    0.37
     выра
    0.36
    實
    0.36
    赶
    0.36
    POSITIVE LOGITS
     मुआव
    0.41
    椛
    0.40
     HeLa
    0.38
    િક્ષ
    0.38
    ⠀
    0.37
    ಚ್ಚ
    0.36
    RATE
    0.36
     bha
    0.36
     curing
    0.36
    ディア
    0.35
    Activations Density 0.015%

    No Known Activations