© 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. 156627
    Prev
    Next
    INDEX
    Explanations

    quality, materials, trust, companies, sometimes

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

    breakdown, parentheses, castle, crack

    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
    淦
    0.48
    機能を
    0.48
     кушымта
    0.48
    িসে
    0.45
    Plain
    0.45
     लिहि
    0.44
    来实现
    0.43
     Glossary
    0.43
    СО
    0.43
     பயன
    0.43
    POSITIVE LOGITS
    ta
    0.50
    šení
    0.45
    ย
    0.41
     godzin
    0.41
    4
    0.41
    ห
    0.40
    the
    0.40
    ття
    0.40
    ट्ट
    0.40
    ovel
    0.40
    Activations Density 0.000%

    No Known Activations