© 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. 159245
    Prev
    Next
    INDEX
    Explanations

    street

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

    wires, story, downloading data

    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
     両
    0.50
     Pavel
    0.47
     Danke
    0.47
     débat
    0.47
    両
    0.47
     会
    0.46
    比較
    0.46
     Cependant
    0.46
     會
    0.45
     紫
    0.45
    POSITIVE LOGITS
     propellant
    0.44
    illings
    0.41
    SERT
    0.41
     substituents
    0.40
     demonstrable
    0.40
     deliverables
    0.40
     intravenous
    0.40
     variously
    0.40
    ogenous
    0.39
     ornamented
    0.39
    Activations Density 0.001%

    No Known Activations