© 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. 112173
    Prev
    Next
    INDEX
    Explanations

    another episode

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

    visual or needing

    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
    pliance
    0.52
     apportionment
    0.48
    clipped
    0.46
    measured
    0.45
    metric
    0.45
    ③
    0.44
    .¹
    0.43
    нням
    0.43
    revenue
    0.43
     ۵
    0.42
    POSITIVE LOGITS
    वा
    0.52
    구
    0.51
    کار
    0.50
     fejleszt
    0.50
    كار
    0.49
    습니다
    0.47
    왤
    0.47
    তামূলক
    0.46
     კარ
    0.46
    ח
    0.46
    Activations Density 0.001%

    No Known Activations