© 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. 160615
    Prev
    Next
    INDEX
    Explanations

    packages and text distribution

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

    software features and harm

    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
     certain
    0.50
    yy
    0.49
     Ks
    0.47
    ic
    0.46
     suburban
    0.46
     Corona
    0.45
    ٹ
    0.44
     interior
    0.43
    2
    0.43
    EL
    0.43
    POSITIVE LOGITS
     журнали
    0.46
     ถาม
    0.45
     文章
    0.43
     activism
    0.43
    沢山
    0.43
     కె
    0.42
     पूछते
    0.42
    这篇文章
    0.42
     执行
    0.41
    journalist
    0.41
    Activations Density 0.001%

    No Known Activations