© 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. 12616
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

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

    JSON keys and values

    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
    rbrakk
    0.47
     erythematosus
    0.45
    ването
    0.45
     proteomics
    0.44
     ট্যাংক
    0.43
     pasien
    0.42
    䨘
    0.42
     quenched
    0.41
    াহরণ
    0.41
     lagen
    0.41
    POSITIVE LOGITS
    1
    0.64
    0.56
    4
    0.52
    0
    0.52
    6
    0.50
    2
    0.50
    番号
    0.48
    9
    0.48
    7
    0.47
    codigo
    0.46
    Activations Density 0.006%

    No Known Activations