© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 197539
    Prev
    Next
    INDEX
    Explanations

    visual or media related

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

    actions, visuals, and positive concepts

    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
    formatted
    0.44
    まで
    0.43
    Respons
    0.43
     (
    0.41
    NB
    0.41
     Presidential
    0.41
     correspondence
    0.41
     formatted
    0.40
     OWL
    0.40
    Master
    0.40
    POSITIVE LOGITS
     तस्वी
    0.54
     फोटोज
    0.52
     pozitiv
    0.51
     kiles
    0.50
     तस्वीरों
    0.50
     мои
    0.49
     glLight
    0.48
     fotoğraf
    0.48
     sottop
    0.48
    涡
    0.47
    Activations Density 0.000%

    No Known Activations