© 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. 123203
    Prev
    Next
    INDEX
    Explanations

    additional questions

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

    violate any rules or don't want

    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
     цих
    0.46
     těch
    0.43
    д
    0.43
     neoplastic
    0.42
    き
    0.42
     solidly
    0.42
    вак
    0.41
    ಹ
    0.41
     progenitor
    0.41
     tých
    0.41
    POSITIVE LOGITS
    🛫
    0.52
     Advisory
    0.50
    ‌های
    0.50
     सुद्धा
    0.50
     Surfaces
    0.49
    👷
    0.49
     интервью
    0.47
     Negotiations
    0.47
    的书
    0.47
    𝙎
    0.46
    Activations Density 0.001%

    No Known Activations