© 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. 126471
    Prev
    Next
    INDEX
    Explanations

    either/don't/have

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

    cells, swim, lawyers, naked, bees, from

    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
    t
    0.52
    dni
    0.49
     مرتب
    0.48
    enqueue
    0.48
     tenements
    0.47
     عندي
    0.46
     interfere
    0.46
    捶
    0.46
    tic
    0.46
     sneaky
    0.46
    POSITIVE LOGITS
    зона
    0.52
     umana
    0.51
    সংযোগ
    0.51
    EL
    0.50
    粛
    0.50
    อกาส
    0.48
    9
    0.47
    ELA
    0.46
    MH
    0.45
    Samsung
    0.45
    Activations Density 0.000%

    No Known Activations