© 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. 241686
    Prev
    Next
    INDEX
    Explanations

    calf areas and heat

    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
     клет
    0.54
     関係
    0.51
    СТЕ
    0.51
    yatiti
    0.51
    朼
    0.50
    ᑭ
    0.49
     пара
    0.48
    RatingDiff
    0.47
     サー
    0.47
     これは
    0.47
    POSITIVE LOGITS
     Ukraine
    0.48
     Diageo
    0.48
     Senin
    0.47
     Commonwealth
    0.47
     not
    0.46
    _{
    0.45
     Opportunity
    0.45
     Dubai
    0.44
    Context
    0.44
    不是
    0.43
    Activations Density 0.003%

    No Known Activations