© 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. 64735
    Prev
    Next
    INDEX
    Explanations

    addresses and numbers

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

    parentheses and special characters

    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
    ClFN
    0.49
     swoim
    0.48
    Aquí
    0.47
     میں
    0.47
     swoich
    0.46
     rispetto
    0.46
     swojego
    0.46
    코
    0.45
     stesso
    0.45
    Super
    0.45
    POSITIVE LOGITS
    তামূলক
    0.45
    aksanaan
    0.41
     Notify
    0.40
    ponible
    0.40
    urkan
    0.40
     modulating
    0.40
     Inserting
    0.39
     Conductivity
    0.39
     notifying
    0.39
     arrhythmia
    0.39
    Activations Density 0.000%

    No Known Activations