© 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. 4973
    Prev
    Next
    INDEX
    Explanations

    Rules, content, names, Columbia

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

    Keywords and categories

    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
     medan
    0.46
    CTOR
    0.45
    UX
    0.44
     dast
    0.44
     י
    0.43
     przed
    0.43
    ｽ
    0.43
     astro
    0.43
     kand
    0.42
     kerana
    0.42
    POSITIVE LOGITS
    гүй
    0.44
     corretamente
    0.43
     Vineyard
    0.42
     /ˈ
    0.42
    </u>
    0.42
     counseling
    0.41
    的使用
    0.39
     फसलों
    0.39
    lső
    0.39
    ajou
    0.38
    Activations Density 0.000%

    No Known Activations