© 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. 227322
    Prev
    Next
    INDEX
    Explanations

    genuine citizen

    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
     $
    0.45
    ACC
    0.44
     યુ
    0.44
     V
    0.43
     только
    0.43
     pesquisa
    0.43
     MDC
    0.43
     oan
    0.43
     BTU
    0.43
     THESE
    0.42
    POSITIVE LOGITS
    warts
    0.53
    Otherwise
    0.52
    Notwithstanding
    0.47
    Else
    0.45
    rists
    0.45
    cars
    0.44
    otonic
    0.43
     Otherwise
    0.43
    𝓲
    0.42
    އ
    0.42
    Activations Density 0.001%

    No Known Activations