© 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. 164124
    Prev
    Next
    INDEX
    Explanations

    ancillary costs, processing, birth, Predator series, impossibility

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

    attribution or reminders

    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
    тыми
    0.51
     অথবা
    0.50
     দেড়
    0.50
     কারনে
    0.48
    или
    0.47
     Или
    0.47
    峀
    0.46
    এক্স
    0.46
     または
    0.45
     yester
    0.45
    POSITIVE LOGITS
    is
    0.43
    postal
    0.41
    roffenen
    0.41
    ryl
    0.40
    라이언트
    0.40
     Reporting
    0.39
    sn
    0.39
    laz
    0.39
     unsatisfactory
    0.39
    监
    0.39
    Activations Density 0.001%

    No Known Activations