© 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. 115088
    Prev
    Next
    INDEX
    Explanations

    multi-language economic and technical terms

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

    configure integration settings

    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
    ц
    0.47
    л
    0.45
     prominently
    0.44
    ↵
    0.43
     insulted
    0.42
    í
    0.42
    า
    0.42
     الثاني
    0.41
     higher
    0.40
     secretly
    0.38
    POSITIVE LOGITS
     داریم
    0.52
     etkin
    0.52
     будем
    0.52
    地铁
    0.50
     kapac
    0.49
     পারিল
    0.48
    鲐
    0.48
    उद्योग
    0.46
     máme
    0.46
     ekonom
    0.46
    Activations Density 0.000%

    No Known Activations