© 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. 16077
    Prev
    Next
    INDEX
    Explanations

    color of, like, a quilt

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

    describing parts, actions, or states

    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
     Exist
    0.45
    ،
    0.44
     phytochemical
    0.44
     Biochemistry
    0.44
    affeine
    0.43
     currant
    0.43
     Oni
    0.41
     Dí
    0.41
    werke
    0.41
     되지
    0.41
    POSITIVE LOGITS
    enfants
    0.44
     намере
    0.44
     ফৌজ
    0.42
     यात्रियों
    0.42
    approx
    0.41
    意
    0.41
     intentions
    0.40
    kHz
    0.40
    жник
    0.39
     pasajeros
    0.39
    Activations Density 0.000%

    No Known Activations