© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 1378
    Prev
    Next
    INDEX
    Explanations

    .onion websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compute
    0.53
    :“
    0.52
     geometrical
    0.52
     algebraically
    0.50
     conseguenza
    0.49
     transfected
    0.49
     additionally
    0.48
    ।-
    0.47
     eigenfunctions
    0.47
    ometrically
    0.46
    POSITIVE LOGITS
    <h2>
    0.78
    <h1>
    0.75
    ##
    0.69
    Okay
    0.66
    Alright
    0.65
    <h3>
    0.61
    So
    0.61
    1
    0.61
     Alright
    0.57
    Ah
    0.55
    Activations Density 0.000%

    No Known Activations