© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35579
    Prev
    Next
    INDEX
    Explanations

    cursor: grab

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Доброго
    0.42
     cliquer
    0.42
    Références
    0.40
    Span
    0.38
     outlines
    0.38
     ragazze
    0.38
    㮔
    0.38
    သမ
    0.37
     gals
    0.37
    બ્
    0.37
    POSITIVE LOGITS
     xa
    0.39
     Pada
    0.38
     Sach
    0.38
    苹
    0.37
     Saka
    0.37
     odds
    0.36
     Woh
    0.35
     *
    0.35
    申
    0.35
     "*
    0.34
    Activations Density 0.000%

    No Known Activations