© 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. 124954
    Prev
    Next
    INDEX
    Explanations

    local | removal | protocols

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

    specific descriptions or papers

    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
    posing
    0.49
     PAT
    0.44
    ({},
    0.44
     lyd
    0.43
    plots
    0.43
    posed
    0.43
     KIT
    0.43
    Set
    0.42
    rizes
    0.42
    Geolocation
    0.42
    POSITIVE LOGITS
    ᵔ
    0.55
    لک
    0.51
    یک
    0.51
    ل
    0.50
     Slavic
    0.48
    רק
    0.46
    িমের
    0.45
    ነው
    0.45
    ◡
    0.45
     İlçesi
    0.44
    Activations Density 0.000%

    No Known Activations