© 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. 69064
    Prev
    Next
    INDEX
    Explanations

    types, either, or

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

    special characters and formatting

    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
     இன்று
    0.47
    ")}}'
    0.42
    moires
    0.42
     apaixon
    0.40
     revolución
    0.40
    ","#
    0.40
     မ
    0.38
     драматур
    0.38
     gioi
    0.38
     আল
    0.38
    POSITIVE LOGITS
     Tak
    0.40
     gating
    0.40
    管
    0.40
    高温
    0.39
    般的
    0.38
    碱
    0.38
     tubing
    0.37
     Overse
    0.37
     Farming
    0.37
     Sequence
    0.37
    Activations Density 0.003%

    No Known Activations