© 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. 155736
    Prev
    Next
    INDEX
    Explanations

    at your own risk

    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
    䀨
    0.56
    မီ
    0.52
    㣫
    0.50
    рон
    0.48
    ዎቹ
    0.47
    рім
    0.47
    㝡
    0.47
    коли
    0.46
    onedDateTime
    0.46
     аксе
    0.46
    POSITIVE LOGITS
    f
    0.50
    l
    0.50
    nobody
    0.46
    percent
    0.46
    乜
    0.45
    belief
    0.44
    pley
    0.44
    ber
    0.44
    berat
    0.43
    urb
    0.43
    Activations Density 0.001%

    No Known Activations