© 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. 99304
    Prev
    Next
    INDEX
    Explanations

    all donors

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

    fraudulent and proprietary information

    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
    ndarray
    0.43
    immon
    0.43
     wiping
    0.41
     tup
    0.40
    विण्यात
    0.40
    ্না
    0.40
    ↵↵
    0.40
    ઓમાં
    0.39
     maupun
    0.39
    lexeme
    0.38
    POSITIVE LOGITS
    getSheet
    0.53
    銨
    0.51
    ORES
    0.49
    氫
    0.47
    錚
    0.46
    ἥ
    0.46
    手
    0.45
     Mathematik
    0.45
    دست
    0.45
    AKE
    0.45
    Activations Density 0.001%

    No Known Activations