© 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. 224207
    Prev
    Next
    INDEX
    Explanations

    out of

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

    cooking instructions and data representation

    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
    ags
    0.45
    ills
    0.44
    BU
    0.43
    aring
    0.41
     некоторым
    0.41
    usages
    0.41
    ˈ
    0.41
     cancellation
    0.41
    ሁ
    0.41
    isc
    0.40
    POSITIVE LOGITS
    ك
    0.55
     eléct
    0.54
     stran
    0.54
    برا
    0.53
    بول
    0.52
     rostro
    0.52
     putem
    0.52
    ،
    0.52
    اشة
    0.50
     cárc
    0.50
    Activations Density 0.000%

    No Known Activations