© 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. 32302
    Prev
    Next
    INDEX
    Explanations

    file structures and code listings

    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
    ，
    0.46
     downside
    0.45
     và
    0.44
    、
    0.44
    ،
    0.43
     description
    0.43
     slabs
    0.43
     downsides
    0.42
     outline
    0.41
     و
    0.41
    POSITIVE LOGITS
    desIP
    0.47
    oLocations
    0.46
    ścic
    0.43
    uuml
    0.42
    abbanti
    0.40
    ennan
    0.40
     對
    0.40
     мла
    0.40
    ufthansa
    0.39
    isOnTimer
    0.39
    Activations Density 0.012%

    No Known Activations