© 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. 134357
    Prev
    Next
    INDEX
    Explanations

    name should

    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
    robots
    0.42
    vollen
    0.42
    воз
    0.39
    razier
    0.39
     дальнейшем
    0.37
     للن
    0.37
     खरा
    0.37
    雳
    0.37
    roboto
    0.36
    ставки
    0.36
    POSITIVE LOGITS
     dependant
    0.45
     dependent
    0.39
     reliant
    0.38
    ག་
    0.38
     guideline
    0.37
    寛
    0.37
     primordial
    0.37
     consist
    0.37
     conduit
    0.37
     ricost
    0.37
    Activations Density 0.000%

    No Known Activations