© 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. 158055
    Prev
    Next
    INDEX
    Explanations

    physical shop

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

    video generation, spells

    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
    CONTENT
    0.51
    (
    0.50
    New
    0.49
    Multi
    0.49
    PER
    0.47
    Round
    0.47
    Sol
    0.47
     multi
    0.46
    Comme
    0.46
    =
    0.46
    POSITIVE LOGITS
     話
    0.47
    扦
    0.43
     enchant
    0.42
    alak
    0.41
     старо
    0.40
     絵
    0.40
    務
    0.40
     obdob
    0.40
    itim
    0.39
     podrían
    0.39
    Activations Density 0.000%

    No Known Activations