© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 137382
    Prev
    Next
    INDEX
    Explanations

    roles and groups

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

    process and understand information

    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
     ابتدائي
    0.52
    0
    0.48
     یہودی
    0.46
     квартира
    0.46
    rieg
    0.45
     فريبي
    0.45
     తల్లి
    0.45
     في
    0.44
     McBride
    0.44
     صالح
    0.44
    POSITIVE LOGITS
     OFF
    0.52
     $\
    0.51
     rozwią
    0.50
     NEEDS
    0.49
     resor
    0.48
     ON
    0.48
     OCR
    0.48
    δα
    0.47
     NI
    0.47
     AISI
    0.46
    Activations Density 0.000%

    No Known Activations