© 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. 7517
    Prev
    Next
    INDEX
    Explanations

    questions and answers

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

    multiple choice options

    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
    Gosudarstvennyj
    0.23
     trialComponents
    0.22
    酊
    0.22
     offsetX
    0.22
     ingrédients
    0.22
     partager
    0.22
     sœurs
    0.21
     zamów
    0.21
     মূর্তি
    0.21
     prostit
    0.21
    POSITIVE LOGITS
    ed
    0.30
    ↵
    0.29
     A
    0.29
    ay
    0.29
    es
    0.28
    A
    0.27
    ade
    0.26
    n
    0.26
    i
    0.26
     Answer
    0.25
    Activations Density 0.061%

    No Known Activations