© 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. 121170
    Prev
    Next
    INDEX
    Explanations

    facts, states, or important details

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

    history in changes

    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
     gên
    0.43
     Well
    0.42
    Parse
    0.42
     runApp
    0.42
    くら
    0.42
     منه
    0.42
     Math
    0.41
     즐
    0.41
     రీ
    0.40
    讓你
    0.40
    POSITIVE LOGITS
    付属品
    0.50
    isors
    0.50
    employees
    0.47
    ي
    0.46
     DJs
    0.45
    accep
    0.45
    ності
    0.45
    يام
    0.44
    us
    0.44
    હ
    0.44
    Activations Density 0.001%

    No Known Activations