© 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. 84281
    Prev
    Next
    INDEX
    Explanations

    separately obtain, polyester fleece, they help

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

    admission, composition, traits, or concerns

    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
    matu
    0.45
    スポ
    0.45
    İ
    0.44
    මාන්
    0.44
    Í
    0.42
    ἱ
    0.42
    啰
    0.41
     กี้
    0.40
    ıyorum
    0.40
    owych
    0.40
    POSITIVE LOGITS
    a
    0.56
     보면
    0.47
     ethics
    0.46
     theatres
    0.45
     nanoparticles
    0.43
     eléctricas
    0.43
     récentes
    0.43
     contactless
    0.42
     repay
    0.42
     ketemu
    0.42
    Activations Density 0.013%

    No Known Activations