© 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. 84739
    Prev
    Next
    INDEX
    Explanations

    specific terms

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

    need, inspire, goals, minimalist

    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
     방정
    0.52
     totalitarian
    0.52
     erreurs
    0.52
     stabbed
    0.51
    ಾಯಿತು
    0.51
    橇
    0.50
    กรณ์
    0.49
     ನಂತರ
    0.48
    カイ
    0.48
     डिल
    0.48
    POSITIVE LOGITS
    يدي
    0.49
    ecto
    0.48
    USR
    0.46
    Attribute
    0.44
    nder
    0.44
    .
    0.44
    ByID
    0.42
     satisfy
    0.41
    مدة
    0.40
    Intrinsic
    0.40
    Activations Density 0.000%

    No Known Activations