© 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. 144049
    Prev
    Next
    INDEX
    Explanations

    worldwide screening

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

    limited freedom

    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
     Jaan
    0.50
    ยาก
    0.48
    Ĕ
    0.47
    י
    0.47
    ომ
    0.46
    łem
    0.46
    ümüş
    0.46
    i
    0.46
    tama
    0.46
     kaise
    0.45
    POSITIVE LOGITS
     الوطني
    0.42
     ڈالر
    0.42
     العالمي
    0.41
    CacheV
    0.40
    strcmp
    0.39
     كث
    0.39
    يمق
    0.39
    冊
    0.39
     globally
    0.38
    }'.
    0.38
    Activations Density 0.000%

    No Known Activations