© 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. 15419
    Prev
    Next
    INDEX
    Explanations

    average swap

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

    illegal or dangerous activities

    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
    rule
    0.45
    like
    0.43
    cel
    0.41
     controller
    0.41
    controlled
    0.40
    iciones
    0.39
     gradual
    0.39
    ഘ
    0.39
     Hem
    0.39
     propi
    0.39
    POSITIVE LOGITS
    勇
    0.48
    년
    0.45
     سنو
    0.44
    車
    0.44
    Бо
    0.44
    ?.
    0.44
     تصل
    0.43
    무
    0.43
     ауди
    0.43
    했고
    0.42
    Activations Density 0.000%

    No Known Activations