© 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. 16632
    Prev
    Next
    INDEX
    Explanations

    assets, firm, invest, Israel, English

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

    recipes use

    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
    同时也
    0.48
    币
    0.46
    Transaction
    0.45
    Variant
    0.44
    ToWrite
    0.44
    אַר
    0.43
    ర్థిక
    0.43
     రాజకీయ
    0.43
     되
    0.43
     उसी
    0.43
    POSITIVE LOGITS
     আশঙ্কা
    0.46
     preth
    0.46
     précédente
    0.45
     samedi
    0.45
     avaient
    0.45
    !
    0.45
     énon
    0.44
     avait
    0.44
    !’
    0.44
     viande
    0.44
    Activations Density 0.000%

    No Known Activations