© 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. 128538
    Prev
    Next
    INDEX
    Explanations

    out of

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

    lists, subjects, and examples

    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
     bolj
    0.53
     supprim
    0.45
    するため
    0.44
    ム
    0.44
    ל
    0.43
     negras
    0.42
    મા
    0.41
    Might
    0.41
    Το
    0.41
    _'+
    0.41
    POSITIVE LOGITS
     தினத்த
    0.50
    aol
    0.48
    kin
    0.46
     Matsumoto
    0.46
    pessoa
    0.46
    fecha
    0.45
    cesa
    0.45
    awas
    0.45
    filename
    0.44
    cite
    0.44
    Activations Density 0.001%

    No Known Activations