© 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. 86433
    Prev
    Next
    INDEX
    Explanations

    getting information from code

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

    code definitions

    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
     detenido
    0.41
     संग्रह
    0.40
     leaky
    0.39
    莳
    0.38
     leak
    0.38
     leaks
    0.38
     soaking
    0.37
     hitam
    0.37
     booze
    0.37
     collection
    0.37
    POSITIVE LOGITS
    combine
    0.44
    Combining
    0.44
    Print
    0.43
    combined
    0.42
    equiv
    0.41
     combines
    0.41
    HTML
    0.41
    √
    0.40
     geeignet
    0.40
    Csv
    0.40
    Activations Density 0.001%

    No Known Activations