© 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. 80535
    Prev
    Next
    INDEX
    Explanations

    acquired at

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

    words to write things like emails or letters

    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
     nhỉ
    0.50
    TeXAtom
    0.48
    𝒚
    0.48
    竿
    0.47
     сель
    0.46
     trường
    0.46
     если
    0.46
     строка
    0.45
     أي
    0.45
     игру
    0.45
    POSITIVE LOGITS
    Jeffrey
    0.52
    Paper
    0.49
    0
    0.49
    We
    0.48
    ala
    0.48
    uh
    0.47
    open
    0.47
    Democrats
    0.47
    Building
    0.46
    Uh
    0.46
    Activations Density 0.001%

    No Known Activations