© 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. 148122
    Prev
    Next
    INDEX
    Explanations

    public information and reproduction

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

    sources of information

    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
    зор
    0.45
    ংকার
    0.44
    ೂರ್
    0.42
    зи
    0.42
    PartOf
    0.42
    瑟
    0.42
     конкурс
    0.40
    础
    0.40
     Crimean
    0.40
    峥
    0.39
    POSITIVE LOGITS
     printr
    0.51
     因此
    0.51
     públicos
    0.50
     ló
    0.50
     synagogues
    0.49
     dicion
    0.48
     dictionary
    0.48
     tedy
    0.47
     więc
    0.47
     gdje
    0.47
    Activations Density 0.002%

    No Known Activations