© 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. 38707
    Prev
    Next
    INDEX
    Explanations

    asking prices

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

    periods and commas

    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
    companies
    0.46
    healthcare
    0.46
    entreprise
    0.45
    В
    0.45
    Brand
    0.43
    challenge
    0.43
    ↵
    0.43
    شركة
    0.42
    Companies
    0.42
    ↵↵
    0.42
    POSITIVE LOGITS
     tolls
    0.47
     callSettings
    0.46
     messageFields
    0.46
     resetCounters
    0.42
     paff
    0.42
     równ
    0.40
     cyclopent
    0.40
     vVertex
    0.39
    㕩
    0.39
     bled
    0.38
    Activations Density 0.001%

    No Known Activations