© 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. 34445
    Prev
    Next
    INDEX
    Explanations

    number points adrift

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

    programming constructs

    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
    獺
    0.44
    коли
    0.42
    インターネット
    0.42
    女
    0.41
    
    0.41
    коло
    0.41
     verbessern
    0.40
    徹
    0.40
    Worlds
    0.39
    коном
    0.38
    POSITIVE LOGITS
     Interfaces
    0.45
    parameters
    0.40
     IUnary
    0.39
     bool
    0.38
     interfaces
    0.38
     Parameters
    0.38
     Industri
    0.37
    getAsDouble
    0.36
     broadcasting
    0.36
     Broadcasting
    0.34
    Activations Density 0.000%

    No Known Activations