© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 29124
    Prev
    Next
    INDEX
    Explanations

    python list operations and search

    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
     thi
    0.43
     source
    0.39
     gewesen
    0.38
    }:
    0.38
    ”:
    0.38
    done
    0.37
    [
    0.37
    preserved
    0.37
     minority
    0.37
    .”
    0.36
    POSITIVE LOGITS
    Filter
    0.44
    ⵔ
    0.43
    μπ
    0.41
    Likes
    0.41
    集
    0.39
    VCTarget
    0.39
    ዴ
    0.38
     Bous
    0.38
     شاء
    0.38
    रोज
    0.37
    Activations Density 0.002%

    No Known Activations