© 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. 174589
    Prev
    Next
    INDEX
    Explanations

    three times annual

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

    vulnerability or vulkan

    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
    ر
    0.51
    나라
    0.49
    ILTON
    0.47
    vider
    0.47
    नं
    0.45
    GU
    0.44
    me
    0.44
    umb
    0.44
    滩
    0.44
    弘
    0.43
    POSITIVE LOGITS
     हे
    0.52
     asistentes
    0.50
     gable
    0.48
     निमित
    0.47
    㩽
    0.46
     twice
    0.45
     উপলক্ষে
    0.45
    ллина
    0.45
     തവണ
    0.44
     फसलों
    0.44
    Activations Density 0.001%

    No Known Activations