© 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. 10967
    Prev
    Next
    INDEX
    Explanations

    items related to technology and interfaces

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

    Corinth, jig, potential, races, faces, errors

    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
    listar
    0.56
    eless
    0.50
    ತಕ್ಕ
    0.50
     їх
    0.49
     करताना
    0.49
    उदा
    0.48
    ｖ
    0.48
    ชน์
    0.48
    ร้อม
    0.47
    і
    0.47
    POSITIVE LOGITS
     —
    0.46
     vê
    0.45
     (!)
    0.45
     (
    0.44
    -
    0.44
     (“
    0.43
     ("
    0.42
     anunció
    0.42
     JPMorgan
    0.42
     –
    0.41
    Activations Density 0.025%

    No Known Activations