© 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. 22418
    Prev
    Next
    INDEX
    Explanations

    total category

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

    list concatenation or combination

    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
     and
    0.44
     with
    0.43
     Dolly
    0.42
    and
    0.40
    لق
    0.40
    댐
    0.39
    with
    0.38
    9
    0.38
    hammer
    0.38
    DW
    0.37
    POSITIVE LOGITS
    上述
    0.43
     unexplored
    0.39
    centaje
    0.39
     keseluruhan
    0.38
     शेष
    0.37
     CATEG
    0.37
     totality
    0.36
     totalidad
    0.36
     prejudices
    0.36
    カテゴ
    0.35
    Activations Density 0.033%

    No Known Activations