© 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. 174943
    Prev
    Next
    INDEX
    Explanations

    systems and regulations involving time, laws, and the world

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

    embossing, etching, insulation, doorways

    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
     경로
    0.53
     기능을
    0.51
    贰
    0.51
     년
    0.50
     პირ
    0.50
     वर्गों
    0.50
     און
    0.49
    仩
    0.49
    椃
    0.49
     곡
    0.48
    POSITIVE LOGITS
     embossing
    0.47
    теше
    0.44
     akik
    0.43
    <sup>
    0.43
     objek
    0.41
     apprehend
    0.41
     bersama
    0.40
     asi
    0.40
     Patriotic
    0.39
    t
    0.39
    Activations Density 0.001%

    No Known Activations