© 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. 148044
    Prev
    Next
    INDEX
    Explanations

    services and locations

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

    trade-offs and consequences

    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
    ᆸ
    0.51
    arie
    0.49
    pages
    0.47
    mortem
    0.47
    zele
    0.47
    ビネット
    0.46
     বের
    0.45
    lists
    0.45
    interview
    0.45
    slit
    0.45
    POSITIVE LOGITS
     intérêts
    0.47
     액세
    0.45
     ograni
    0.45
    辊
    0.43
     صنعتی
    0.42
    Accordingly
    0.42
     nasz
    0.41
     गंगा
    0.41
     Optionen
    0.41
     עס
    0.41
    Activations Density 0.000%

    No Known Activations