© 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. 52210
    Prev
    Next
    INDEX
    Explanations

    you regardless, we know, enjoy the

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

    Denial, variance, travel, ops

    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
    <unused1049>
    0.50
    ิ
    0.49
     哦
    0.45
     DEFAULT
    0.44
     נו
    0.44
     ২৬
    0.43
     ব্রাজ
    0.43
     οποίος
    0.43
     $^{
    0.42
     马
    0.42
    POSITIVE LOGITS
    集
    0.46
     spyware
    0.44
    ším
    0.43
     oynuyoruz
    0.43
    ceğim
    0.43
    jších
    0.43
     zucchero
    0.42
    つもり
    0.42
     znam
    0.42
    *)(
    0.42
    Activations Density 0.000%

    No Known Activations