© 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. 189878
    Prev
    Next
    INDEX
    Explanations

    transportation lines

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

    section headings and lists

    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
    ½
    0.57
     of
    0.56
    4
    0.53
    3
    0.52
    ¼
    0.50
    1
    0.49
     on
    0.49
    5
    0.49
    insurance
    0.48
     that
    0.48
    POSITIVE LOGITS
     மெட்ரோ
    0.64
    즌
    0.55
     기본적인
    0.54
    <unused79>
    0.52
     préparer
    0.52
     Empresas
    0.52
     வால்பேப்பர்கள்
    0.50
     Конечно
    0.49
     స్థాప
    0.49
     preparar
    0.48
    Activations Density 0.000%

    No Known Activations