© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 106997
    Prev
    Next
    INDEX
    Explanations

    open house day

    np_acts-logits-general · gemini-2.5-flash-lite

    verify context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unbelievably
    0.50
     मोठ
    0.46
    big
    0.46
    만을
    0.45
    τή
    0.45
     шести
    0.45
    หนึ่ง
    0.44
    곁
    0.44
    ставля
    0.43
    chied
    0.43
    POSITIVE LOGITS
     vérifier
    0.46
     situatie
    0.43
     sewers
    0.43
     resolvers
    0.42
     sytuacji
    0.42
     >>=
    0.41
     context
    0.40
     susceptibility
    0.40
     verify
    0.40
     açısından
    0.40
    Activations Density 0.005%

    No Known Activations