© 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. 99040
    Prev
    Next
    INDEX
    Explanations

    game results

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

    avoiding unnecessary or harmful content

    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
     affirm
    0.43
    )=(
    0.43
     á
    0.43
     পুরু
    0.42
     trebui
    0.41
     firmness
    0.40
     Beth
    0.40
    )/(
    0.40
     sy
    0.40
    }+(\
    0.40
    POSITIVE LOGITS
    кономи
    0.44
    ১৯
    0.44
     Anaconda
    0.43
    ع
    0.42
     madrugada
    0.42
    RUPTION
    0.42
     Belf
    0.41
    UMO
    0.41
    ಿಕ್
    0.41
    िनी
    0.41
    Activations Density 0.000%

    No Known Activations