© 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. 98543
    Prev
    Next
    INDEX
    Explanations

    other or approval notice

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

    file, trigger, default, write

    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
    textColour
    0.48
    輥
    0.45
     Chakra
    0.44
    ческа
    0.43
    يانة
    0.43
    璉
    0.43
    िक्रमा
    0.42
    <unused77>
    0.42
    fdPar
    0.41
    chemia
    0.41
    POSITIVE LOGITS
     public
    0.48
    classic
    0.45
     playbook
    0.45
    fileName
    0.44
    ùi
    0.44
     fileName
    0.44
     conjunction
    0.43
     nationale
    0.43
    大
    0.43
    cdn
    0.42
    Activations Density 0.000%

    No Known Activations