© 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. 131546
    Prev
    Next
    INDEX
    Explanations

    hidden categories, season, friendly advertising

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

    common issues and origins

    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
    "،
    0.51
     ज़्यादा
    0.48
    }}}\
    0.47
    ।"
    0.46
     inne
    0.46
    }.")
    0.45
    laat
    0.45
    ".
    0.44
    ubes
    0.44
     لكن
    0.43
    POSITIVE LOGITS
    ୫
    0.52
     χω
    0.50
    اعری
    0.46
    ')$
    0.46
    ଧ
    0.45
     gating
    0.45
     boston
    0.45
     richi
    0.43
     комиссии
    0.42
    টর
    0.42
    Activations Density 0.000%

    No Known Activations