© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 3635
    Prev
    Next
    INDEX
    Explanations

    supportive colleagues, discovered that, no subtle

    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
     with
    0.58
    Le
    0.56
    ly
    0.54
    ak
    0.52
    te
    0.51
    As
    0.51
    Con
    0.50
     a
    0.49
    era
    0.49
    Per
    0.49
    POSITIVE LOGITS
    fdPar
    0.59
     revê
    0.55
     coorden
    0.55
    ){}^
    0.55
     குறு
    0.54
     horrid
    0.54
     cerc
    0.53
    ‹
    0.53
     croche
    0.52
     простых
    0.52
    Activations Density 0.000%

    No Known Activations