© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13517
    Prev
    Next
    INDEX
    Explanations

    flat head screwdriver

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

    explanatory phrases

    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_16k_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
    -(\
    0.44
    ŕ
    0.43
    mittance
    0.43
    orche
    0.41
    ropole
    0.41
    še
    0.40
    łos
    0.40
    ē
    0.40
    LE
    0.40
    ou
    0.40
    POSITIVE LOGITS
     bác
    0.47
     बल्लेबाज
    0.43
     عندي
    0.43
     мной
    0.41
    我说
    0.41
     Reply
    0.41
     আমি
    0.41
     irgendwie
    0.40
     నేను
    0.40
     χρόνο
    0.40
    Activations Density 0.099%

    No Known Activations