© 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. 73172
    Prev
    Next
    INDEX
    Explanations

    multifaceted collections

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

    distribution, interpolation

    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
    EXPL
    0.54
     إلي
    0.48
    ListData
    0.46
    Terminology
    0.45
     ఎ
    0.44
     extré
    0.42
     éché
    0.42
    ChessBot
    0.42
     ర
    0.42
     елект
    0.42
    POSITIVE LOGITS
     providers
    0.50
    ேன்
    0.49
     hues
    0.48
     apartment
    0.45
    マンション
    0.43
     provider
    0.43
    ygon
    0.43
     refurbishment
    0.41
    avro
    0.41
     advantage
    0.41
    Activations Density 0.000%

    No Known Activations