© 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. 3980
    Prev
    Next
    INDEX
    Explanations

    end of, once a, mural every

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

    for each / at each

    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
    Trusted
    0.50
    n
    0.48
    Copy
    0.45
    Ste
    0.42
    Tell
    0.42
     Reprint
    0.42
    copy
    0.41
     Copy
    0.41
     لما
    0.41
    In
    0.41
    POSITIVE LOGITS
     tonal
    0.54
    উন্ড
    0.47
     UIS
    0.47
     jede
    0.46
     TON
    0.46
    <unused22>
    0.45
     tamam
    0.45
     EACH
    0.45
     wheelchairs
    0.45
     hairdry
    0.45
    Activations Density 0.000%

    No Known Activations