© 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. 44803
    Prev
    Next
    INDEX
    Explanations

    return authorization

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

    commands and states

    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
    wikimedia
    0.54
    iour
    0.52
     έγ
    0.51
    ្ម
    0.50
     மிசோ
    0.50
    unities
    0.49
     делу
    0.49
     ờ
    0.48
    ան
    0.48
    ađ
    0.48
    POSITIVE LOGITS
    令和
    0.58
    Span
    0.51
     Kranken
    0.46
    Trace
    0.45
     ?
    0.44
     Ausstellung
    0.44
    0.44
    堃
    0.44
    Poster
    0.44
     Repert
    0.44
    Activations Density 0.001%

    No Known Activations