© 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. 88697
    Prev
    Next
    INDEX
    Explanations

    beads, tube, attach, created, particle

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

    React useRef hook

    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
    🦸
    0.52
     ಜಿಲ್ಲ
    0.49
     जिले
    0.48
     વૃક્ષ
    0.48
     удалить
    0.47
    функ
    0.47
    繋がりたい
    0.46
    district
    0.46
     निधि
    0.46
    🕵
    0.46
    POSITIVE LOGITS
     in
    0.56
     and
    0.54
     stopped
    0.53
     -
    0.53
     Eller
    0.53
     Voss
    0.52
     p
    0.51
     scho
    0.50
     Minnesota
    0.48
     doesn
    0.48
    Activations Density 0.000%

    No Known Activations