© 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. 135142
    Prev
    Next
    INDEX
    Explanations

    company names and stock symbols

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

    company stock information

    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
     Capri
    0.45
    Vari
    0.42
     Büyük
    0.41
    ><?
    0.39
     clichés
    0.38
     Boulevard
    0.38
     --->
    0.38
     <
    0.37
    Kau
    0.37
    Brend
    0.37
    POSITIVE LOGITS
    YNAMICS
    0.45
     wages
    0.44
    িবেন
    0.44
     insure
    0.43
     maintain
    0.43
     sustains
    0.43
     aliquot
    0.42
    식회사
    0.42
    पोरेशन
    0.42
     mixts
    0.42
    Activations Density 0.003%

    No Known Activations