© 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. 32631
    Prev
    Next
    INDEX
    Explanations

    evaluation, assessment, and verification

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

    all levels and states

    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
     water
    0.50
     tenemos
    0.47
     agua
    0.47
    haven
    0.46
     WATER
    0.46
     stove
    0.46
     protection
    0.45
     ロ
    0.44
     RED
    0.44
     our
    0.44
    POSITIVE LOGITS
     যাচাই
    0.54
     статисти
    0.53
     relembrar
    0.48
    评价
    0.46
    评估
    0.46
    概率
    0.45
     yanıt
    0.45
     તેમના
    0.45
     প্রতিবেদক
    0.44
    审核
    0.44
    Activations Density 0.001%

    No Known Activations