© 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. 52181
    Prev
    Next
    INDEX
    Explanations

    list of items and tasks

    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
     oxygen
    0.50
    ht
    0.47
     application
    0.46
    '
    0.44
     urea
    0.44
    AT
    0.44
    ST
    0.44
     accuracy
    0.43
     efficiency
    0.43
     option
    0.42
    POSITIVE LOGITS
    ⏸
    0.66
     gelişmeler
    0.56
     expressões
    0.55
    🎏
    0.54
     🎉
    0.54
     Tatha
    0.54
     Architektur
    0.53
     Seja
    0.53
     Sejam
    0.52
     singoli
    0.52
    Activations Density 0.005%

    No Known Activations