© 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. 90135
    Prev
    Next
    INDEX
    Explanations

    engineering solutions

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

    sustainablekind ofsustainablekind of

    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
     ヒ
    0.51
    屶
    0.49
    ｼ
    0.47
     copa
    0.47
     特に
    0.46
     マル
    0.46
     prestig
    0.45
     הג
    0.45
    も含
    0.45
    pct
    0.45
    POSITIVE LOGITS
    是一种
    0.52
    దే
    0.47
    水
    0.46
    边
    0.45
     köş
    0.44
    工程师
    0.42
     Coord
    0.41
     Acoustics
    0.41
    是个
    0.41
    难度
    0.40
    Activations Density 0.000%

    No Known Activations