© 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. 149656
    Prev
    Next
    INDEX
    Explanations

    health problems and outcomes

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

    explaining why someone or something is notable

    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
     álgebra
    0.46
     estadísticas
    0.46
    都没有
    0.46
    䒿
    0.45
     całkow
    0.45
     पैसों
    0.44
    appart
    0.43
    Carta
    0.43
    Amounts
    0.43
     caract
    0.43
    POSITIVE LOGITS
    界面
    0.44
    隔離
    0.41
     border
    0.40
    入口
    0.40
    端
    0.40
    LINE
    0.40
    ync
    0.39
    सीमा
    0.39
     西
    0.38
     、
    0.38
    Activations Density 0.001%

    No Known Activations