© 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. 53-GEMMASCOPE-2-RES-65K
    7. 3996
    Prev
    Next
    INDEX
    Explanations

    lamp shades and finials

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

    specific entry points

    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_53_width_65k_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
    嶇
    0.40
    示范
    0.40
    ryw
    0.39
     חו
    0.39
     دھ
    0.36
     доход
    0.36
     بج
    0.36
    asam
    0.35
     doctr
    0.35
    坷
    0.35
    POSITIVE LOGITS
    íss
    0.43
    ﻄ
    0.39
     আব্দ
    0.38
    FFE
    0.37
    IZED
    0.36
    περι
    0.36
    ொரு
    0.36
     Cortés
    0.35
    GRA
    0.35
     Lucille
    0.35
    Activations Density 0.000%

    No Known Activations