© 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-65K
    7. 30351
    Prev
    Next
    INDEX
    Explanations

    what does it encompass

    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_65k_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
     کھیلتے
    0.49
     yaklaşık
    0.48
    禳
    0.47
    كان
    0.47
     සං
    0.46
     کھیلنے
    0.46
     अनुबंध
    0.44
     الرئيسي
    0.44
     cancelar
    0.44
     francese
    0.43
    POSITIVE LOGITS
    /
    0.47
    ogh
    0.39
    ,
    0.39
     at
    0.38
     rounds
    0.38
     trenches
    0.38
     buds
    0.37
     shortcuts
    0.37
     slack
    0.37
     from
    0.36
    Activations Density 0.000%

    No Known Activations