© 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. 164093
    Prev
    Next
    INDEX
    Explanations

    financial year

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

    categorize by 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
     aziende
    0.48
    設立
    0.44
    録
    0.44
     deň
    0.43
    萬
    0.42
    確保
    0.42
    開催
    0.41
     estimado
    0.41
    ّ
    0.41
    Cidade
    0.41
    POSITIVE LOGITS
     Christina
    0.45
    ক্তির
    0.42
     माध
    0.41
     gifted
    0.41
     mediation
    0.41
    Christina
    0.41
     которая
    0.40
     Diagram
    0.40
     специфи
    0.40
     copyrights
    0.39
    Activations Density 0.001%

    No Known Activations