© 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-16K
    7. 12069
    Prev
    Next
    INDEX
    Explanations

    stole second, clicking submit

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

    Google, requirements, metadata

    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_16k_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
    א
    0.58
     آهنگ
    0.56
    وند
    0.52
    کے
    0.50
    觟
    0.49
    సె
    0.48
    WordArray
    0.47
    Ⲏ
    0.47
    צ
    0.46
    𝄞
    0.46
    POSITIVE LOGITS
     UNA
    0.51
     UNITED
    0.49
     future
    0.48
     MATRIX
    0.48
    future
    0.47
     deterministic
    0.47
     Guant
    0.47
     foreseeable
    0.46
    et
    0.46
     quantifiable
    0.46
    Activations Density 0.003%

    No Known Activations