© 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. 60047
    Prev
    Next
    INDEX
    Explanations

    safety rules and guidance

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

    Bell weather case

    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
     v
    0.50
     tutto
    0.48
    현재
    0.46
     Ingles
    0.45
     wirtschaft
    0.45
    conditioned
    0.44
     feria
    0.44
    "
    0.44
     igualmente
    0.43
     we
    0.43
    POSITIVE LOGITS
    чеб
    0.51
     chłop
    0.49
    ฐาน
    0.49
     सरस्व
    0.49
    销
    0.48
     भूषण
    0.48
    čių
    0.46
    ชนะ
    0.46
    沿着
    0.46
     ሽፋ
    0.46
    Activations Density 0.000%

    No Known Activations