© 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. 62965
    Prev
    Next
    INDEX
    Explanations

    searching for information or guidance

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

    code blocks and scripts

    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
    q
    0.49
    体验
    0.48
    op
    0.47
    atik
    0.47
    el
    0.45
    etik
    0.45
    vius
    0.45
    etas
    0.44
    stvo
    0.44
    enskap
    0.43
    POSITIVE LOGITS
     matches
    0.49
    魷
    0.49
     macroeconomic
    0.46
     segu
    0.45
    コーナー
    0.45
     hubby
    0.45
    RCC
    0.43
     funzioni
    0.43
     材質
    0.42
    場合がございます
    0.42
    Activations Density 0.000%

    No Known Activations