© 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. 33808
    Prev
    Next
    INDEX
    Explanations

    demographics or technical concepts

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

    computations and branches

    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
    hadap
    0.52
    jv
    0.52
     भी
    0.52
    ａ
    0.52
     sebagai
    0.51
    owali
    0.51
     également
    0.51
     vreme
    0.51
    janja
    0.51
    <0x80>
    0.50
    POSITIVE LOGITS
    Integration
    0.46
     visualizations
    0.45
     integrations
    0.45
     optimizations
    0.45
     iterating
    0.44
    哞
    0.43
     subsequ
    0.43
     мате
    0.42
    Translations
    0.42
     Localization
    0.42
    Activations Density 0.000%

    No Known Activations