© 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. 95433
    Prev
    Next
    INDEX
    Explanations

    locations, announcements, or details

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

    detection logic

    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
     proprie
    0.59
     ガラス
    0.58
     caráter
    0.57
     cómo
    0.56
     pré
    0.55
     molten
    0.55
     店
    0.54
     instituições
    0.52
     institución
    0.51
     gră
    0.51
    POSITIVE LOGITS
    on
    0.48
    or
    0.46
    Email
    0.44
    ir
    0.44
    service
    0.43
    t
    0.43
    even
    0.42
    sning
    0.42
    Marg
    0.42
    ospel
    0.42
    Activations Density 0.000%

    No Known Activations