© 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. 49434
    Prev
    Next
    INDEX
    Explanations

    positive outcomes and action

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

    example usage

    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
    7
    0.54
    3
    0.49
    4
    0.48
    5
    0.47
    8
    0.47
     также
    0.45
     نیز
    0.43
    9
    0.43
    ி
    0.43
    mdan
    0.42
    POSITIVE LOGITS
     be
    0.52
     হইতে
    0.51
    ClearedBy
    0.50
    ȩ
    0.49
     کے
    0.47
     бути
    0.45
     攵
    0.45
     ہے
    0.44
     اخذنا
    0.44
    ă
    0.43
    Activations Density 0.140%

    No Known Activations