© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 26345
    Prev
    Next
    INDEX
    Explanations

    announcements and submissions

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

    November dates

    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
    وير
    0.50
    msgs
    0.42
     महिन्यात
    0.40
    重建
    0.40
     sovereignty
    0.39
    ويم
    0.39
     vudd
    0.38
    跨
    0.38
     ඉක්
    0.38
    zaXR
    0.38
    POSITIVE LOGITS
     lot
    0.44
    one
    0.44
     partic
    0.44
    otten
    0.43
    만한
    0.42
     :
    0.42
    ott
    0.40
     लिखे
    0.40
    CRP
    0.40
     стро
    0.40
    Activations Density 0.000%

    No Known Activations