© 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. 177511
    Prev
    Next
    INDEX
    Explanations

    competent licence solutions

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

    defining parameters directly

    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
    чеб
    0.47
    择
    0.43
    setFooter
    0.43
    ెండు
    0.42
    Toolbar
    0.41
    щено
    0.41
     плане
    0.41
    庸
    0.41
    償
    0.41
    ሏ
    0.41
    POSITIVE LOGITS
    ſ
    0.57
    یہ
    0.47
    ollip
    0.46
    ਯ
    0.44
    ਰ
    0.43
    tera
    0.42
    imported
    0.42
    fathers
    0.42
    ی
    0.42
    referred
    0.42
    Activations Density 0.000%

    No Known Activations