© 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. 199434
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific events

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

    consider unplugging

    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
     è
    0.52
     ništa
    0.47
    əsi
    0.47
    不得不
    0.47
    駁
    0.46
    usta
    0.45
     claridad
    0.45
    è
    0.45
     点
    0.44
     szkoły
    0.44
    POSITIVE LOGITS
    걔
    0.52
     તેઓ
    0.46
     WrestleMania
    0.46
     आजम
    0.46
     चूंकि
    0.43
    ravenous
    0.43
    UEFA
    0.42
     रण
    0.41
    ي
    0.41
     overworked
    0.41
    Activations Density 0.000%

    No Known Activations