© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 191162
    Prev
    Next
    INDEX
    Explanations

    Scheme and JavaScript programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Detroit
    0.59
    Detroit
    0.57
    介
    0.41
    Ford
    0.39
    habt
    0.38
    Separator
    0.38
    separator
    0.38
     компет
    0.37
     Calabria
    0.37
    Fiat
    0.37
    POSITIVE LOGITS
    樱
    0.39
    洱
    0.38
     biển
    0.38
     frees
    0.37
     beaches
    0.36
     Lime
    0.36
     leach
    0.36
     larch
    0.36
     Pure
    0.35
     Qiu
    0.35
    Activations Density 0.003%

    No Known Activations