© 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-262K
    7. 43706
    Prev
    Next
    INDEX
    Explanations

    comparing limitations vs

    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
    2
    0.61
    5
    0.59
    8
    0.54
    9
    0.52
    Char
    0.52
    3
    0.52
    في
    0.49
    4
    0.49
    7
    0.48
    Just
    0.48
    POSITIVE LOGITS
     применение
    0.50
     solicita
    0.48
     distinguer
    0.48
     semelhantes
    0.46
     commemorating
    0.45
     применять
    0.45
     PGR
    0.45
     비슷한
    0.45
     Ramadan
    0.44
     tinkering
    0.44
    Activations Density 0.002%

    No Known Activations