© 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. 64865
    Prev
    Next
    INDEX
    Explanations

    locations and local concepts

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

    text analysis and system properties

    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
    en
    0.54
    is
    0.50
    ان
    0.49
    ен
    0.49
    itely
    0.49
    androidx
    0.48
    n
    0.48
    Questions
    0.47
    adex
    0.47
    ter
    0.47
    POSITIVE LOGITS
    援
    0.46
     locale
    0.45
     làng
    0.43
     Scream
    0.43
     locales
    0.42
     hollow
    0.42
     പഞ്ചായ
    0.42
     tradeoff
    0.42
     unto
    0.41
     confided
    0.41
    Activations Density 0.000%

    No Known Activations