© 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. 10290
    Prev
    Next
    INDEX
    Explanations

    conjunctions connecting concepts

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

    detailed explanation

    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
    $>
    0.64
    $
    0.58
    =
    0.57
    ίναι
    0.51
    镓
    0.51
    ला
    0.51
    यला
    0.49
    بر
    0.49
    $，
    0.48
    ვე
    0.48
    POSITIVE LOGITS
    amp
    1.27
    mdash
    0.98
    ndash
    0.89
    nbsp
    0.76
    hellip
    0.70
     to
    0.70
     &
    0.69
    Amp
    0.65
    quot
    0.65
    ldquo
    0.64
    Activations Density 0.129%

    No Known Activations