© 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. 114954
    Prev
    Next
    INDEX
    Explanations

    dates and ages

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

    consent or sleep

    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
    তি
    0.44
    風景
    0.42
    %
    0.42
    ædia
    0.40
    ío
    0.39
     souls
    0.39
     души
    0.39
    タ
    0.39
     quartiers
    0.38
     брак
    0.38
    POSITIVE LOGITS
    ）；
    0.39
    ），
    0.39
    пион
    0.39
    keb
    0.38
     ef
    0.38
     ogen
    0.38
     camber
    0.37
     conver
    0.37
     epoxide
    0.37
    fromString
    0.37
    Activations Density 0.007%

    No Known Activations