© 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. 69836
    Prev
    Next
    INDEX
    Explanations

    Shipping USA

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

    how to split a pill

    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
     Canvas
    0.54
     Lily
    0.52
     Root
    0.52
     Place
    0.52
     Pary
    0.52
    i
    0.51
    Cherry
    0.49
     Health
    0.49
     Rugby
    0.49
    Berry
    0.49
    POSITIVE LOGITS
    インド
    0.47
    ;')
    0.47
    チャート
    0.47
     rookies
    0.46
    BURSEMENTS
    0.45
    <bos>
    0.44
    いますが
    0.44
    えます
    0.43
     resonators
    0.43
    ディー
    0.43
    Activations Density 0.001%

    No Known Activations