© 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. 158539
    Prev
    Next
    INDEX
    Explanations

    showcased support for imagination engines

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

    statistical approaches

    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
    ro
    0.55
    la
    0.53
    skii
    0.52
     previo
    0.50
     ہیں۔
    0.50
    rules
    0.49
     ভুট্ট
    0.49
    Ợ
    0.49
    rr
    0.49
     जस्टिस
    0.48
    POSITIVE LOGITS
     penchant
    0.47
    Arkadaşlar
    0.44
    Hallo
    0.42
     foodie
    0.42
     installer
    0.42
    או
    0.41
     staunch
    0.40
    マル
    0.40
    ем
    0.39
    داء
    0.39
    Activations Density 0.001%

    No Known Activations