© 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. 156505
    Prev
    Next
    INDEX
    Explanations

    fireworks, proprietor, installation

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

    pronoun antecedents and specificity

    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
    am
    0.56
    config
    0.52
     config
    0.45
    ंबी
    0.44
    戰
    0.44
    azuje
    0.43
    amiseks
    0.43
    ically
    0.43
    CONFIG
    0.42
    Soccer
    0.42
    POSITIVE LOGITS
    шенные
    0.47
     особенности
    0.47
     unin
    0.47
     impediments
    0.46
     специали
    0.46
     препят
    0.46
     cálculos
    0.45
    ỹ
    0.45
     предмет
    0.45
     austenitic
    0.45
    Activations Density 0.001%

    No Known Activations