© 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. 64203
    Prev
    Next
    INDEX
    Explanations

    tech, law, health, specific nouns

    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
    кой
    0.45
    وی
    0.43
    ٸ
    0.42
    व्यक्तित्व
    0.42
    Mz
    0.42
    𝙧
    0.42
    함으로써
    0.40
    ej
    0.40
    默默
    0.40
    YA
    0.39
    POSITIVE LOGITS
    alink
    0.46
     Sailing
    0.44
    üst
    0.43
    aste
    0.42
    inor
    0.41
     Tackle
    0.41
    alic
    0.40
    ennis
    0.40
    ill
    0.40
    犄
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.