© 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. 44638
    Prev
    Next
    INDEX
    Explanations

    our dedicated

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

    GRID size

    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
    d
    0.63
    v
    0.62
    g
    0.61
    w
    0.55
    h
    0.54
    j
    0.54
    andia
    0.51
    t
    0.51
    y
    0.51
    drift
    0.49
    POSITIVE LOGITS
     სპეცი
    0.59
    𝚂
    0.57
     ニ
    0.55
     מאוד
    0.55
    ᑖ
    0.54
     ඔහු
    0.54
     สมการ
    0.53
     NSLog
    0.53
     เสียง
    0.52
    ᴱ
    0.52
    Activations Density 0.000%

    No Known Activations