© 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. 134681
    Prev
    Next
    INDEX
    Explanations

    forward-looking statements, employee training, garments

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

    describing product features

    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
    oplay
    0.49
    attend
    0.46
    ILayout
    0.44
    FLO
    0.44
    CORD
    0.43
    EDIT
    0.43
    ধারণ
    0.42
    兰
    0.42
    ulin
    0.41
     ற
    0.41
    POSITIVE LOGITS
    hun
    0.49
     merger
    0.49
    സിയ
    0.48
    ne
    0.48
     менедж
    0.48
    šenje
    0.47
    hut
    0.47
    스로
    0.46
    که
    0.46
    シング
    0.46
    Activations Density 0.000%

    No Known Activations