© 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. 163491
    Prev
    Next
    INDEX
    Explanations

    individual litigation

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

    initializes object creation

    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
    Semaphore
    0.53
    สอง
    0.51
    🧣
    0.50
     पहनी
    0.50
     सेमी
    0.47
     العلوم
    0.47
     कैप्शन
    0.47
    肆章
    0.47
     Саме
    0.47
    मग
    0.47
    POSITIVE LOGITS
     sales
    0.52
     industrial
    0.52
    value
    0.51
    파
    0.51
    林
    0.49
    ái
    0.48
     in
    0.47
    德
    0.47
     aggressive
    0.46
     forwarding
    0.46
    Activations Density 0.000%

    No Known Activations