© 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. 36762
    Prev
    Next
    INDEX
    Explanations

    new follower

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

    dangerous voltages arc

    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
    :
    0.51
     giphy
    0.49
     naturais
    0.48
     jan
    0.48
    s
    0.47
     lembra
    0.47
     descend
    0.47
    }=
    0.47
     siti
    0.47
     máxim
    0.46
    POSITIVE LOGITS
    परेट
    0.46
    াণিত
    0.45
    াপনের
    0.45
    oprene
    0.43
    Malaysia
    0.43
    lemy
    0.42
    餑
    0.42
    唛
    0.42
    umbing
    0.42
    ⵥ
    0.42
    Activations Density 0.000%

    No Known Activations