© 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. 223065
    Prev
    Next
    INDEX
    Explanations

    academic or specific topics

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

    setting options

    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
     ಸಮಸ್ಯ
    0.52
    хема
    0.51
     วิ
    0.47
     บ
    0.45
     доме
    0.44
     преимущества
    0.44
     Welch
    0.43
     инде
    0.43
    nomes
    0.43
     conjectured
    0.43
    POSITIVE LOGITS
     on
    0.58
    Setting
    0.51
     setting
    0.48
    setting
    0.48
    設定
    0.45
    薹
    0.44
    ɹ
    0.43
    ert
    0.43
     with
    0.42
    ater
    0.41
    Activations Density 0.000%

    No Known Activations