© 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. 191910
    Prev
    Next
    INDEX
    Explanations

    words followed by common continuations

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

    Ultimate Oscillator, chemicals, Pineapple, Rachel

    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
    requenz
    0.49
     suppressed
    0.49
    აგ
    0.44
     ע
    0.43
     מע
    0.42
    [
    0.42
    γ
    0.42
    γκ
    0.42
     ước
    0.42
    iembre
    0.42
    POSITIVE LOGITS
     झाल्यावर
    0.49
    เพื่อให้
    0.47
     Aś
    0.45
    setError
    0.43
     duit
    0.42
     ഡോ
    0.42
     Operate
    0.42
    TakeVideo
    0.42
    সাইন
    0.42
    setOutput
    0.41
    Activations Density 0.000%

    No Known Activations