© 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. 204028
    Prev
    Next
    INDEX
    Explanations

    one sentence

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

    Residential Schedule

    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
     side
    0.47
     trimethyl
    0.46
    肩
    0.46
     atmos
    0.44
    涡
    0.43
     aank
    0.43
     potential
    0.41
    باس
    0.41
    weise
    0.40
     metaphys
    0.40
    POSITIVE LOGITS
    cons
    0.57
    etc
    0.56
    imetable
    0.52
    {},
    0.52
    el
    0.51
    indir
    0.51
    marca
    0.51
    subj
    0.50
    elie
    0.49
    $;
    0.49
    Activations Density 0.001%

    No Known Activations