© 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. 42743
    Prev
    Next
    INDEX
    Explanations

    coloring pages

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

    topics from texts

    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
     voldoende
    0.46
    ی
    0.44
    决定
    0.43
    
    0.43
    🆒
    0.43
     FAC
    0.42
     Reward
    0.41
    
    0.41
     entscheiden
    0.41
    î
    0.41
    POSITIVE LOGITS
    corrh
    0.49
     生地
    0.46
    ρί
    0.46
    водит
    0.44
    ようです
    0.44
     seaside
    0.44
    рида
    0.44
     திருதியை
    0.43
    urnya
    0.43
     pecados
    0.43
    Activations Density 0.008%

    No Known Activations