© 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. 244894
    Prev
    Next
    INDEX
    Explanations

    property, gift, child, banner

    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
     erfol
    0.55
     L
    0.52
    LL
    0.47
     l
    0.44
     LL
    0.44
     EYE
    0.44
     může
    0.42
    AT
    0.42
     racconta
    0.42
     même
    0.42
    POSITIVE LOGITS
    Santiago
    0.57
    siswa
    0.51
    墀
    0.48
    பிலோ
    0.48
    뢨
    0.47
    బ్బు
    0.47
    Dashboard
    0.46
    Christopher
    0.46
    лосо
    0.46
    rendre
    0.46
    Activations Density 0.000%

    No Known Activations