© 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. 2474
    Prev
    Next
    INDEX
    Explanations

    business services and fees

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

    business and technical topics

    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
     water
    0.43
     destroyed
    0.42
     neutrinos
    0.41
     水
    0.41
     macroscopic
    0.41
     movies
    0.40
     mesons
    0.40
     particles
    0.39
     animals
    0.39
     larvae
    0.39
    POSITIVE LOGITS
     Fintech
    0.45
    的市场
    0.44
     HubSpot
    0.42
     финансо
    0.41
     SaaS
    0.41
    Парт
    0.41
    💼
    0.41
    LinkedIn
    0.41
    经纪
    0.40
    奚
    0.40
    Activations Density 0.257%

    No Known Activations