© 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. 121255
    Prev
    Next
    INDEX
    Explanations

    financial or functional contexts

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

    created by AI

    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
     ただ
    0.48
    dependence
    0.45
     লোকে
    0.44
     ઝ
    0.43
     প্রতিদিন
    0.43
    indent
    0.43
     دوران
    0.42
    Indent
    0.42
     قرض
    0.42
    Mix
    0.42
    POSITIVE LOGITS
     purposely
    0.44
     yoki
    0.44
    谋
    0.44
    itys
    0.44
     funkci
    0.44
     comercial
    0.43
     ekonom
    0.43
     traiter
    0.43
     fys
    0.43
     veya
    0.42
    Activations Density 0.001%

    No Known Activations