© 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. 163522
    Prev
    Next
    INDEX
    Explanations

    correct all violations

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

    starts with Jean or Val

    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
    illin
    0.44
    icio
    0.43
    uji
    0.43
    ’
    0.43
    Continuous
    0.43
    oso
    0.42
    osos
    0.42
     النهايات
    0.42
    ane
    0.42
    fut
    0.42
    POSITIVE LOGITS
     வீடியோ
    0.57
     listrik
    0.54
     comenzó
    0.53
     frå
    0.53
    쓱
    0.52
     empezó
    0.52
     vás
    0.52
     humide
    0.52
     vídeo
    0.51
     vaš
    0.51
    Activations Density 0.001%

    No Known Activations