© 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. 158075
    Prev
    Next
    INDEX
    Explanations

    verbs initiating phrases

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

    logging, backing, rounded up, wiping out, speed up

    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
     an
    0.71
    ED
    0.70
    U
    0.68
     l
    0.68
    UD
    0.65
    2
    0.63
    s
    0.62
    ের
    0.62
    ites
    0.61
    те
    0.61
    POSITIVE LOGITS
    a
    0.61
    加以
    0.57
     câte
    0.55
    <unused2130>
    0.54
    ’।
    0.53
    <unused2222>
    0.53
    אַ
    0.52
    क्राफ्ट
    0.52
    看出
    0.51
     excer
    0.51
    Activations Density 0.160%

    No Known Activations