© 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. 219394
    Prev
    Next
    INDEX
    Explanations

    address

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

    end of punctuated statements

    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
     Swain
    0.47
    i
    0.44
     unlock
    0.40
     Acres
    0.40
    fields
    0.39
    quinone
    0.39
    Lock
    0.39
     Acre
    0.39
    ION
    0.39
    attach
    0.39
    POSITIVE LOGITS
    埝
    0.51
    überküloz
    0.47
    ण्ट
    0.47
    குழந்த
    0.46
     matematika
    0.46
    წერა
    0.46
     velocidad
    0.46
    हात
    0.45
     детей
    0.45
     sağlıklı
    0.45
    Activations Density 0.000%

    No Known Activations