© 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. 3166
    Prev
    Next
    INDEX
    Explanations

    progress and load status

    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
    amsmath
    0.44
    Cómo
    0.43
    绺
    0.42
     arasındaki
    0.42
    鸪
    0.42
    olischen
    0.42
     అన్ని
    0.41
    Quién
    0.41
    谢
    0.40
     Recherches
    0.40
    POSITIVE LOGITS
    progress
    0.50
    ⌛
    0.46
     progress
    0.46
    uptime
    0.44
    Progress
    0.43
     (%)
    0.42
     loads
    0.42
    load
    0.41
     whatsoever
    0.41
     futures
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.