© 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. 97182
    Prev
    Next
    INDEX
    Explanations

    permanent holiday

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

    multiply by delta

    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
     собак
    0.50
     Проци
    0.50
    る
    0.47
    Ⲓ
    0.47
    ི
    0.46
    🤽
    0.46
    物质
    0.46
     нужда
    0.46
     Органи
    0.46
    陆
    0.45
    POSITIVE LOGITS
    ل
    0.52
    xel
    0.46
    ج
    0.46
    ANCED
    0.44
    ভ
    0.44
    jedno
    0.44
    すが
    0.43
     piens
    0.43
    Gaussian
    0.42
     možno
    0.42
    Activations Density 0.000%

    No Known Activations