© 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. 196758
    Prev
    Next
    INDEX
    Explanations

    rated school

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

    owls and college

    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
    enemy
    0.52
    Enemy
    0.51
    augh
    0.50
    rotate
    0.50
     เหมือน
    0.49
     миллионов
    0.49
    以内
    0.48
    𒈬
    0.48
    lev
    0.48
    したので
    0.47
    POSITIVE LOGITS
     elemen
    0.54
    것
    0.49
     amphibians
    0.46
     Owls
    0.46
     dioxane
    0.46
     entrer
    0.46
     owls
    0.45
    o
    0.44
     Owl
    0.44
    ંદ
    0.43
    Activations Density 0.000%

    No Known Activations