© 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. 122202
    Prev
    Next
    INDEX
    Explanations

    areas, level, or subject

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

    how kinky

    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
    瞬
    0.49
    첫
    0.48
    ל
    0.47
    即
    0.46
    泰
    0.46
     Instant
    0.46
    卽
    0.46
     Transvaal
    0.46
    恒
    0.45
    筅
    0.45
    POSITIVE LOGITS
    pisah
    0.46
     الموضوع
    0.45
    loch
    0.44
     کررہ
    0.44
     lalu
    0.44
     সংশোধন
    0.44
     কর্মচার
    0.43
    selectable
    0.43
    altung
    0.43
    uttle
    0.43
    Activations Density 0.000%

    No Known Activations