© 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. 84707
    Prev
    Next
    INDEX
    Explanations

    we | our | before

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

    views or translate

    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
    +++
    0.45
     memastikan
    0.45
    新增
    0.43
    ・
    0.43
     कायम
    0.43
    }+
    0.42
    bert
    0.42
    争取
    0.42
    stream
    0.42
    答
    0.42
    POSITIVE LOGITS
    옮
    0.47
    vì
    0.47
     ш
    0.47
     каме
    0.47
     logarith
    0.47
     tremble
    0.45
    １
    0.45
    л
    0.45
    ко
    0.44
     inco
    0.44
    Activations Density 0.000%

    No Known Activations