© 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. 10460
    Prev
    Next
    INDEX
    Explanations

    starting to do

    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
     endeavoured
    0.39
     groaned
    0.39
    }\,\
    0.38
     rise
    0.38
    ({})
    0.38
    ismos
    0.37
    AMENTE
    0.36
    Phoenix
    0.36
     yawn
    0.36
     sensibilities
    0.36
    POSITIVE LOGITS
     Doing
    0.39
     جو
    0.39
     худож
    0.39
    ngthen
    0.38
     Nathaniel
    0.38
    解釋
    0.38
     店
    0.37
    孳
    0.37
     Nelson
    0.37
     یک
    0.37
    Activations Density 0.000%

    No Known Activations