© 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. 115275
    Prev
    Next
    INDEX
    Explanations

    looking at choices

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

    lost, decomposition, controlling, learning, cause, collection

    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
    🕛
    0.49
     priorité
    0.48
     elongate
    0.47
    Zeneca
    0.47
    延长
    0.45
    西兰
    0.45
    🕐
    0.44
    ｶ
    0.44
    的時候
    0.44
    넬
    0.44
    POSITIVE LOGITS
    d
    0.60
    m
    0.55
     FAST
    0.53
    /
    0.52
     And
    0.51
     Healing
    0.51
     Bracket
    0.51
     Ignition
    0.49
     Gr
    0.49
     Finally
    0.48
    Activations Density 0.000%

    No Known Activations