© 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. 180709
    Prev
    Next
    INDEX
    Explanations

    information lists

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

    security risks

    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
    用
    0.50
    і
    0.49
    不太
    0.46
    在
    0.45
    ichte
    0.44
    )}')
    0.43
    人
    0.43
    量
    0.42
     ভারতে
    0.41
    加拿大
    0.41
    POSITIVE LOGITS
     đẳng
    0.52
     bangunan
    0.50
     pretended
    0.50
     pecados
    0.49
     रेपो
    0.46
    maxn
    0.46
     sanding
    0.46
    pe
    0.46
     bilhões
    0.46
    rizes
    0.45
    Activations Density 0.000%

    No Known Activations