© 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. 14612
    Prev
    Next
    INDEX
    Explanations

    writing and supplier activity

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

    technical terms and descriptions

    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
    Em
    0.63
    Il
    0.51
    Carlton
    0.51
    א
    0.48
    A
    0.48
    UO
    0.48
    J
    0.47
    רג
    0.47
    ADD
    0.46
    Eat
    0.46
    POSITIVE LOGITS
    <unused2>
    0.52
     serían
    0.51
    lamualaikum
    0.50
     व्याव
    0.49
    <unused24>
    0.48
     flurry
    0.47
     فیصلے
    0.47
    <unused28>
    0.46
     chłop
    0.45
    imantan
    0.45
    Activations Density 0.000%

    No Known Activations