© 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. 221779
    Prev
    Next
    INDEX
    Explanations

    UC Berkeley

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

    describing qualities

    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
    ளுடைய
    0.48
    ᱶ
    0.44
    íonn
    0.43
    यर
    0.43
    니
    0.43
    өк
    0.42
    िरण
    0.42
     lê
    0.42
    ັນ
    0.42
    ᄌ
    0.41
    POSITIVE LOGITS
    regist
    0.58
    Dataset
    0.55
    Node
    0.52
    dataType
    0.51
    s
    0.50
     confessions
    0.50
     Пока
    0.49
     عش
    0.49
     daffodils
    0.49
     ثلاث
    0.47
    Activations Density 0.000%

    No Known Activations