© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 213298
    Prev
    Next
    INDEX
    Explanations

    common use case

    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
     בדי
    0.46
    弇
    0.45
     Eta
    0.44
    羮
    0.44
    ymax
    0.44
    amax
    0.41
    beatCounter
    0.41
    刓
    0.41
    äm
    0.40
    错过
    0.40
    POSITIVE LOGITS
    pick
    0.40
     modules
    0.40
    pers
    0.38
    outh
    0.37
     contained
    0.37
    lection
    0.37
     reproduction
    0.36
    small
    0.36
     plugin
    0.36
    light
    0.35
    Activations Density 0.000%

    No Known Activations