© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85238
    Prev
    Next
    INDEX
    Explanations

    parent/children, Jackson renegotiates

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

    using `xhost +local:`

    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
    Negative Logits
    ClNO
    0.51
     ২০২৩
    0.49
    జేపీ
    0.46
     ప్రక
    0.45
    ക്കാര
    0.45
     खोल
    0.45
     också
    0.45
    డీపీ
    0.44
    蒈
    0.44
     ২৫
    0.44
    POSITIVE LOGITS
    ilians
    0.49
    늘
    0.47
    uli
    0.47
     dure
    0.46
     suffis
    0.46
    igenschaften
    0.46
     convexes
    0.46
    languages
    0.45
     langue
    0.45
    ummers
    0.45
    Activations Density 0.000%

    No Known Activations