© 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. 53-GEMMASCOPE-2-RES-262K
    7. 11988
    Prev
    Next
    INDEX
    Explanations

    numeric parameters and ranges

    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_53_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
    لاح
    0.43
    邵
    0.41
    appendix
    0.40
     maanden
    0.40
     ไอ้
    0.40
    getCharAt
    0.40
    Eli
    0.39
    脌
    0.39
     επισ
    0.38
    ᗩ
    0.38
    POSITIVE LOGITS
     rules
    0.44
     fraction
    0.41
     wiped
    0.41
    fraction
    0.39
    ioni
    0.38
     decim
    0.38
     tease
    0.37
    Requirement
    0.37
    param
    0.37
     fractional
    0.37
    Activations Density 0.034%

    No Known Activations