© 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. 237253
    Prev
    Next
    INDEX
    Explanations

    similar format

    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
    ल
    0.55
    لبية
    0.50
    t
    0.47
     lanzar
    0.46
     lighter
    0.45
     lanz
    0.44
     yan
    0.41
     benar
    0.41
     Saving
    0.41
    ت
    0.41
    POSITIVE LOGITS
    からも
    0.50
     ረ
    0.47
    Doom
    0.45
    uele
    0.45
     пережи
    0.45
    祜
    0.44
     Dom
    0.44
    PCT
    0.43
    quasi
    0.43
     だ
    0.43
    Activations Density 0.001%

    No Known Activations