© 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. 159695
    Prev
    Next
    INDEX
    Explanations

    pay you

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

    not perfect or basic representation

    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
    тно
    0.55
     увеличения
    0.50
    ג
    0.50
    μι
    0.49
    昉
    0.49
    מר
    0.49
     disminución
    0.47
    铬
    0.47
    针
    0.46
    攀
    0.46
    POSITIVE LOGITS
    as
    0.57
    o
    0.54
    register
    0.54
    state
    0.48
    teenage
    0.47
    row
    0.47
    search
    0.47
    ostream
    0.47
    offic
    0.47
    email
    0.46
    Activations Density 0.001%

    No Known Activations