© 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. 31-GEMMASCOPE-2-RES-65K
    7. 63448
    Prev
    Next
    INDEX
    Explanations

    file size vs quality

    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_31_width_65k_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
     restful
    0.49
     인간
    0.48
    밂
    0.47
     abaixo
    0.46
    نج
    0.46
     nacionales
    0.46
     setActive
    0.45
    randrange
    0.44
    삵
    0.44
     nonparametric
    0.43
    POSITIVE LOGITS
     Air
    0.47
     Wharf
    0.47
    upan
    0.44
     Eaton
    0.44
    Output
    0.44
     ma
    0.42
     Bullet
    0.41
     Coast
    0.41
    Bullet
    0.40
    Air
    0.40
    Activations Density 0.001%

    No Known Activations