© 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. 129380
    Prev
    Next
    INDEX
    Explanations

    activities and events

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

    links to model information

    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
    相当于
    0.50
    第四
    0.49
     multiples
    0.45
    生气
    0.45
    '.
    0.45
    在
    0.45
    )$
    0.45
     Virology
    0.45
    久
    0.43
    मध्ये
    0.43
    POSITIVE LOGITS
     mã
    0.50
    rentes
    0.49
     comuni
    0.48
    ITAR
    0.46
     aplicações
    0.45
    esy
    0.45
    TextStyle
    0.45
    Straße
    0.45
    ukiyoe
    0.45
    rete
    0.44
    Activations Density 0.000%

    No Known Activations