© 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. 30868
    Prev
    Next
    INDEX
    Explanations

    phrase completion

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

    property protection

    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
    ים
    0.66
    ↵
    0.63
    R
    0.62
    LL
    0.61
    IA
    0.61
    X
    0.60
    MS
    0.60
    H
    0.59
    Z
    0.58
    ED
    0.57
    POSITIVE LOGITS
    อยาก
    0.60
     unworthy
    0.55
     sueños
    0.54
     insanely
    0.54
    ﮏ
    0.54
     royaume
    0.53
     blatantly
    0.53
     exclaimed
    0.52
     väldigt
    0.52
     valore
    0.52
    Activations Density 0.000%

    No Known Activations