© 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. 1665
    Prev
    Next
    INDEX
    Explanations

    Specific entities after separators

    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
    ،
    0.43
    ，
    0.34
    .
    0.28
    、
    0.27
    "،
    0.26
    "",
    0.25
     ،
    0.24
    "],
    0.23
    
    0.23
    parsedBlock
    0.23
    POSITIVE LOGITS
    n
    0.29
    s
    0.27
     illetve
    0.25
    d
    0.25
     które
    0.25
    a
    0.24
     které
    0.23
    is
    0.23
    im
    0.22
    א
    0.22
    Activations Density 0.412%

    No Known Activations