© 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. 125018
    Prev
    Next
    INDEX
    Explanations

    why questions

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

    paid than

    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
    စိတ်အပိုင်း
    0.53
    栝
    0.48
    %，
    0.47
     penyebab
    0.46
     justo
    0.46
     Remembering
    0.46
     WORDS
    0.46
     لمح
    0.45
     despised
    0.45
    郗
    0.45
    POSITIVE LOGITS
    IEnumerable
    0.46
    IEN
    0.46
    є
    0.45
    踴
    0.44
    Overlay
    0.44
    dynam
    0.43
    ogy
    0.43
    intera
    0.43
    tight
    0.42
    Gap
    0.42
    Activations Density 0.001%

    No Known Activations