© 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. 10819
    Prev
    Next
    INDEX
    Explanations

    legal proceedings

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

    Swahili and African country names

    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
     ríos
    0.45
    سطس
    0.42
    olist
    0.41
     mening
    0.41
    녕
    0.41
     ince
    0.40
     vagu
    0.40
    USAGE
    0.40
    聞き
    0.40
    कद
    0.39
    POSITIVE LOGITS
    讓我們
    0.40
    "="
    0.37
    ="
    0.36
    计算机
    0.36
     clarifications
    0.36
    立方
    0.36
     लोकप्रिय
    0.36
    患
    0.36
     Traveling
    0.35
    锦
    0.35
    Activations Density 0.004%

    No Known Activations