© 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. 109804
    Prev
    Next
    INDEX
    Explanations

    this is simple

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

    NavigationView code structure

    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
    0.55
    9
    0.53
    2
    0.52
    8
    0.52
     possessing
    0.52
    3
    0.51
    1
    0.47
     कामया
    0.47
    6
    0.47
    kovskij
    0.46
    POSITIVE LOGITS
     les
    0.47
     copertura
    0.46
    修理
    0.45
     correctement
    0.44
    知的
    0.44
     siquiera
    0.44
    р
    0.44
     però
    0.43
    🍘
    0.43
    горе
    0.43
    Activations Density 0.000%

    No Known Activations