© 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. 125926
    Prev
    Next
    INDEX
    Explanations

    April Ryan Net Worth

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

    adjective + noun descriptions

    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
    forgot
    0.45
     нагре
    0.43
    п
    0.43
    fry
    0.43
    renerg
    0.43
    breath
    0.43
    경상
    0.42
    watering
    0.42
    killing
    0.42
     किराया
    0.40
    POSITIVE LOGITS
    لاع
    0.51
    阵
    0.46
     militaire
    0.45
     혹은
    0.45
     bởi
    0.44
    表情
    0.44
     आर्मी
    0.44
     Communism
    0.43
     boxers
    0.43
     établissements
    0.42
    Activations Density 0.011%

    No Known Activations