© 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. 195880
    Prev
    Next
    INDEX
    Explanations

    signed lifetime

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

    phase and context

    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
     satış
    0.54
     sprzedaży
    0.54
    kę
    0.50
     wafer
    0.49
    𝐁
    0.49
    ຜະລິດຕະພັນ
    0.49
    出售
    0.48
     uffic
    0.47
    ũ
    0.47
    。（
    0.47
    POSITIVE LOGITS
    Caucasian
    0.45
     मजबूत
    0.45
     mumkin
    0.44
     ਉਹ
    0.43
    Classical
    0.43
    pues
    0.42
     مجموع
    0.42
    Denominator
    0.41
    Witness
    0.41
    ᔪ
    0.41
    Activations Density 0.001%

    No Known Activations