© 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. 240877
    Prev
    Next
    INDEX
    Explanations

    ensure future proportions lost alarm lifting

    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
    cknowledg
    0.60
    ⨔
    0.57
    GTUIKit
    0.57
    ስቃሴ
    0.56
    ację
    0.55
     বানিয়ে
    0.53
    )]),
    0.52
    蚪
    0.52
    番号
    0.51
     ہتھیار
    0.51
    POSITIVE LOGITS
    repr
    0.54
     Therm
    0.50
    in
    0.49
    ຍ
    0.48
     beant
    0.47
     rep
    0.47
     therm
    0.47
    therm
    0.47
    ↵↵
    0.46
     e
    0.46
    Activations Density 0.001%

    No Known Activations