© 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. 148225
    Prev
    Next
    INDEX
    Explanations

    portal and platform access

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

    GPS, Bloom, brace, Small

    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
     Bellingham
    0.55
     Murat
    0.50
     Gustavo
    0.47
     Dae
    0.47
    逭
    0.46
     Webster
    0.45
     Montevideo
    0.45
    ()?;
    0.45
     Monmouth
    0.44
     Gustav
    0.44
    POSITIVE LOGITS
    ਰ
    0.51
    рата
    0.50
     caída
    0.47
    گر
    0.47
    ம்பிய
    0.47
    地に
    0.46
    Эк
    0.45
     vendido
    0.44
     incapacity
    0.44
    a
    0.44
    Activations Density 0.000%

    No Known Activations