© 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. 148532
    Prev
    Next
    INDEX
    Explanations

    gifts of transport or services

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

    if i could technically

    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
    滪
    0.51
     şirket
    0.45
     Religions
    0.45
    认可
    0.45
    艺术
    0.44
     ലാ
    0.44
    MENTS
    0.44
     النبي
    0.44
     Artistic
    0.43
     Aquinas
    0.43
    POSITIVE LOGITS
    mix
    0.50
    ifelse
    0.47
     incurring
    0.46
    ambarkan
    0.45
    ᆷ
    0.43
    ϑ
    0.43
    使い
    0.43
    elbow
    0.43
    infra
    0.43
    lmfit
    0.43
    Activations Density 0.001%

    No Known Activations