© 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. 54208
    Prev
    Next
    INDEX
    Explanations

    youtube links and pic.twitter.com links

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

    youtube video links

    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
     conces
    0.56
     SLAs
    0.51
     carnaval
    0.50
     PACS
    0.49
     FACS
    0.49
     멤버
    0.49
     новогод
    0.47
     베
    0.47
     Infinix
    0.47
    솝
    0.47
    POSITIVE LOGITS
    ud
    0.67
    q
    0.67
    j
    0.64
    ba
    0.64
    and
    0.63
    na
    0.62
    ir
    0.59
    ua
    0.59
    isa
    0.59
    zy
    0.58
    Activations Density 0.003%

    No Known Activations