© 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. 182281
    Prev
    Next
    INDEX
    Explanations

    together means

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

    starting phrase

    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
     auxilia
    0.52
    🥢
    0.48
     arbej
    0.47
    মস
    0.47
     அலுவலக
    0.46
    詆
    0.46
     அலுவ
    0.45
    داول
    0.44
     pelayanan
    0.44
     kalt
    0.44
    POSITIVE LOGITS
    ಕ್ರ
    0.52
     huge
    0.52
    huge
    0.50
    FK
    0.47
     hydrocarbon
    0.47
    ఆర్‌
    0.44
    readdir
    0.44
     뽑
    0.42
    blk
    0.42
    exported
    0.42
    Activations Density 0.000%

    No Known Activations