© 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. 41205
    Prev
    Next
    INDEX
    Explanations

    organizations related to business

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

    thinking choices labeling

    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
    惊讶
    0.50
     удиви
    0.49
     Elektrokhimiya
    0.46
     benzoic
    0.46
     Roop
    0.46
    一脸
    0.46
     ጭ
    0.46
    震惊
    0.45
    了这个
    0.45
     పూర్తి
    0.44
    POSITIVE LOGITS
     companies
    0.48
    TAM
    0.48
    organizations
    0.46
     employers
    0.46
     workplaces
    0.45
    SPRING
    0.45
     organizations
    0.44
     relationships
    0.44
    UR
    0.44
    ਰ
    0.43
    Activations Density 0.001%

    No Known Activations