© 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. 76768
    Prev
    Next
    INDEX
    Explanations

    costs $

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

    island construction and physics concepts

    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
     Recordings
    0.46
    কি
    0.46
     Styl
    0.46
    KA
    0.44
     Creative
    0.44
     Spelling
    0.44
    ફે
    0.43
    ?
    0.43
    Creative
    0.43
    لی
    0.43
    POSITIVE LOGITS
     pourrait
    0.50
     каждой
    0.50
    enstein
    0.48
     молока
    0.48
     :{
    0.48
    auteur
    0.47
    amant
    0.47
    m
    0.47
    en
    0.47
    opponent
    0.46
    Activations Density 0.000%

    No Known Activations