© 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. 145998
    Prev
    Next
    INDEX
    Explanations

    local businesses and implants

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

    identify input fields

    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
     ث
    0.48
     garb
    0.48
     கட்சியின்
    0.46
     monadic
    0.44
     juggling
    0.44
     صرف
    0.44
     بالکل
    0.43
    に基づ
    0.43
    ナトリウム
    0.42
     வைத்துக்
    0.42
    POSITIVE LOGITS
    uhan
    0.51
    ESS
    0.47
    et
    0.47
    黃
    0.46
    Hur
    0.46
    olab
    0.46
    tees
    0.45
    ה
    0.45
    كرة
    0.45
    ù
    0.45
    Activations Density 0.000%

    No Known Activations