© 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. 33365
    Prev
    Next
    INDEX
    Explanations

    programming models

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

    modelmodels and code definitions

    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
    alp
    0.47
    ısında
    0.47
    ictures
    0.44
    莽
    0.42
    迅速
    0.42
    <0x80>
    0.41
    闷
    0.41
    InvariantCulture
    0.41
    虑
    0.40
     бібліоте
    0.40
    POSITIVE LOGITS
    clazz
    0.46
    جل
    0.46
     esclusivamente
    0.43
    equilibrium
    0.42
     ujian
    0.42
     V
    0.42
     thuring
    0.42
     Haj
    0.42
     J
    0.41
     delegate
    0.41
    Activations Density 0.000%

    No Known Activations