© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22834
    Prev
    Next
    INDEX
    Explanations

    size of the universe

    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_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
    requested
    0.46
    وک
    0.44
    BR
    0.44
     名称
    0.44
    бу
    0.43
    theme
    0.42
    к
    0.42
    compliance
    0.42
    fonts
    0.41
    configuration
    0.41
    POSITIVE LOGITS
     Intermediate
    0.48
     intermediate
    0.46
    lyde
    0.45
     Newsletter
    0.43
    我认为
    0.43
    ̍
    0.43
    ťa
    0.43
     Carlyle
    0.42
     Nonlinear
    0.41
    するために
    0.41
    Activations Density 0.001%

    No Known Activations