© 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. 53492
    Prev
    Next
    INDEX
    Explanations

    right side

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

    leading to consequences

    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
    centroid
    0.49
    텐
    0.44
    thon
    0.43
    정과
    0.42
     pressure
    0.40
     integrative
    0.40
    蒨
    0.40
    圧力
    0.40
     legitimately
    0.39
    압
    0.39
    POSITIVE LOGITS
    '!
    0.52
     obeying
    0.48
     erreur
    0.46
     мог
    0.46
     aiut
    0.46
     धोखा
    0.45
     upholding
    0.44
     dandruff
    0.44
     первая
    0.44
    🐥
    0.44
    Activations Density 0.000%

    No Known Activations