© 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. 116084
    Prev
    Next
    INDEX
    Explanations

    growth access life

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

    Buddha, finally, concept, separate, account

    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
     Aquarelle
    0.52
     Hör
    0.51
    قدر
    0.51
    s
    0.51
    m
    0.50
    k
    0.48
    gü
    0.48
    K
    0.48
     Na
    0.47
     Glasgow
    0.47
    POSITIVE LOGITS
     ভূ
    0.49
     adversaries
    0.49
    enemies
    0.48
     बाएं
    0.47
    <0x87>
    0.46
     ор
    0.45
    係る
    0.45
    regator
    0.45
     bereavement
    0.45
     ګرځ
    0.45
    Activations Density 0.004%

    No Known Activations