© 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. 13859
    Prev
    Next
    INDEX
    Explanations

    amounts, claims, stars, interior, effectiveness, must

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

    any input or provided text

    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
     resultante
    0.42
    หล
    0.41
    resulting
    0.40
     n
    0.39
     resulting
    0.39
     nii
    0.38
     Los
    0.38
    列
    0.38
     conductor
    0.37
    的总
    0.37
    POSITIVE LOGITS
    诒
    0.40
     μέρος
    0.39
    ર્ક
    0.39
    вної
    0.39
     আব্দ
    0.39
     πρέπει
    0.38
    vykor
    0.38
     ύ
    0.37
    ucose
    0.37
     abdom
    0.36
    Activations Density 0.000%

    No Known Activations