© 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. 136721
    Prev
    Next
    INDEX
    Explanations

    "I" Think, "and" Speak

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

    Proper nouns and voice

    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
    osy
    0.53
    +}$,
    0.50
     एमटीएस
    0.47
    irons
    0.45
     Chop
    0.44
    ouche
    0.44
     झर
    0.44
    रोवर
    0.43
    ₂,
    0.43
    OC
    0.43
    POSITIVE LOGITS
     jedan
    0.50
     één
    0.45
    جيل
    0.45
    س
    0.44
     kolo
    0.44
     ain
    0.43
    墨西哥
    0.43
     Nigeria
    0.43
    ۰
    0.42
     siste
    0.42
    Activations Density 0.001%

    No Known Activations