© 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. 21590
    Prev
    Next
    INDEX
    Explanations

    lists of items separated by commas

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

    economic liberalization, systems, detection, apparatus

    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
    op
    0.50
    pp
    0.49
    la
    0.47
    ap
    0.46
     cirk
    0.46
     lak
    0.45
    -
    0.45
     kon
    0.45
     palk
    0.45
    au
    0.44
    POSITIVE LOGITS
    بی
    0.53
    ﮟ
    0.48
     সমাজে
    0.47
    دی
    0.47
    ანი
    0.45
    スケ
    0.45
    𝓻
    0.45
    ည်း
    0.45
    archiwizowane
    0.45
    𝓼
    0.45
    Activations Density 0.000%

    No Known Activations