© 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. 126743
    Prev
    Next
    INDEX
    Explanations

    corporate branding

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

    underway, foresight, immediate

    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
    orten
    0.40
     준비
    0.39
    虬
    0.39
     owned
    0.38
     Remember
    0.38
    িন্দু
    0.38
    ћа
    0.38
    ਕ
    0.38
     Upcoming
    0.38
     persiapan
    0.38
    POSITIVE LOGITS
    formerly
    0.50
     fortiter
    0.46
    herald
    0.46
     secu
    0.46
     institu
    0.45
    election
    0.43
     impenetr
    0.42
     lét
    0.41
     sır
    0.41
    эро
    0.41
    Activations Density 0.000%

    No Known Activations