© 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. 245525
    Prev
    Next
    INDEX
    Explanations

    speaking speaking creation

    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
    '
    0.46
     adequately
    0.44
     I
    0.42
    ?[
    0.42
    _
    0.42
    ?";
    0.41
    ?)
    0.40
    "
    0.39
    iget
    0.39
    azs
    0.39
    POSITIVE LOGITS
     gonflement
    0.59
     takiego
    0.55
     pouvant
    0.55
     sprechen
    0.54
     permettant
    0.52
    ालत
    0.52
    خواندن
    0.52
     dépassant
    0.51
     chiedere
    0.50
     création
    0.49
    Activations Density 0.001%

    No Known Activations