© 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. 73555
    Prev
    Next
    INDEX
    Explanations

    financing available

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

    rules and conditions

    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
     ɖ
    0.47
     harden
    0.47
     svih
    0.47
     curt
    0.47
    掣
    0.46
    ٰی
    0.46
     convoy
    0.46
     spree
    0.46
     thermodynam
    0.45
     сложи
    0.45
    POSITIVE LOGITS
    Olympic
    0.52
    езде
    0.48
    о
    0.45
     Names
    0.44
    郎
    0.44
    ழ்ப
    0.43
    <i>
    0.43
    ber
    0.43
    duplicate
    0.43
    toilet
    0.42
    Activations Density 0.002%

    No Known Activations