© 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. 188636
    Prev
    Next
    INDEX
    Explanations

    driving and health advisories

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

    accessible export Figma

    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
    OURCES
    0.51
    ﺖ
    0.47
    [,,"
    0.45
     rupani
    0.44
    貴
    0.44
     abate
    0.44
    owali
    0.43
    гает
    0.43
     trialComponents
    0.43
    hoy
    0.43
    POSITIVE LOGITS
     Reykjavik
    0.50
    ന്ന്
    0.44
     Intern
    0.43
    िक
    0.43
     Misty
    0.43
     Augen
    0.43
    ിക്കുകയും
    0.43
    嘏
    0.43
    സ്ഥ
    0.42
     Schengen
    0.42
    Activations Density 0.001%

    No Known Activations