© 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. 76929
    Prev
    Next
    INDEX
    Explanations

    foreign characters or specific words

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

    always review

    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
     কাগ
    0.48
     parameterType
    0.45
     Computation
    0.43
    裂
    0.43
     Luật
    0.41
     changement
    0.40
    霑
    0.39
     perturbation
    0.39
    应对
    0.39
    信息化
    0.39
    POSITIVE LOGITS
    މ
    0.48
    ョ
    0.47
     происходит
    0.47
    *,
    0.46
     homers
    0.46
    Auf
    0.46
     دائما
    0.46
    '},
    0.45
    *
    0.45
     ܀
    0.45
    Activations Density 0.000%

    No Known Activations