© 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. 208605
    Prev
    Next
    INDEX
    Explanations

    Early, Using, Common, One

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

    gather evidence or details

    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
     unanimously
    0.45
     for
    0.42
    أت
    0.42
    c
    0.42
     androidx
    0.40
    ็น
    0.40
     Coming
    0.40
    сно
    0.39
     station
    0.38
     Zamora
    0.38
    POSITIVE LOGITS
    presentable
    0.54
    或
    0.53
     रिच
    0.50
    䀘
    0.49
     கரைய
    0.48
     चाहें
    0.48
     Renata
    0.48
     ਅਤੇ
    0.47
     හෝ
    0.47
     பொருட்களை
    0.47
    Activations Density 0.002%

    No Known Activations