© 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. 33982
    Prev
    Next
    INDEX
    Explanations

    later months

    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
     amusement
    0.40
    these
    0.38
    <?=$
    0.38
    〉
    0.37
     >;
    0.37
     полага
    0.36
    してお
    0.36
    tier
    0.35
     Wander
    0.35
     asm
    0.35
    POSITIVE LOGITS
    傃
    0.45
    务
    0.40
     बाध्य
    0.39
    氶
    0.38
    楧
    0.38
    ாதார
    0.38
     इस्लाम
    0.38
    盜
    0.38
    ويلة
    0.37
    ौती
    0.37
    Activations Density 0.000%

    No Known Activations