© 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. 188305
    Prev
    Next
    INDEX
    Explanations

    editorial notes

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

    incorporates elements

    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
    en
    0.52
    ibu
    0.49
    ק
    0.49
    s
    0.48
    ，
    0.47
    a
    0.47
    layout
    0.45
    e
    0.44
    ya
    0.43
    se
    0.43
    POSITIVE LOGITS
    也将
    0.47
     disminución
    0.47
     instinctive
    0.46
     reposition
    0.45
    કમ
    0.45
     esfuer
    0.44
     മല
    0.44
     गर्व
    0.44
     ngunit
    0.44
    ާމ
    0.44
    Activations Density 0.000%

    No Known Activations