© 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. 4278
    Prev
    Next
    INDEX
    Explanations

    names following conjunctions/commas

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

    names following "named" or "old"

    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
    学者
    0.32
    end
    0.31
    bound
    0.30
    world
    0.30
    <0x0D>
    0.30
    sklearn
    0.29
    making
    0.29
    iation
    0.29
    associated
    0.29
    proj
    0.28
    POSITIVE LOGITS
     Olivia
    0.41
     Víctor
    0.41
     Emily
    0.40
     Adrián
    0.39
     Amanda
    0.38
     família
    0.38
     Kayla
    0.38
     Policía
    0.38
     李
    0.38
     Belinda
    0.38
    Activations Density 0.090%

    No Known Activations