© 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. 32239
    Prev
    Next
    INDEX
    Explanations

    table headers

    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
    #
    0.50
     ©
    0.46
    rizes
    0.46
     *
    0.40
       
    0.39
     Oh
    0.39
     characterizing
    0.38
    <0x99>
    0.38
     eigens
    0.38
    ※
    0.38
    POSITIVE LOGITS
    нняя
    0.52
    贴
    0.51
    ک
    0.49
     стадии
    0.47
    磕
    0.46
    த்தை
    0.45
     Collie
    0.44
     करिकुलम
    0.44
     கான்
    0.43
     سلاټونه
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.