© 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. 98036
    Prev
    Next
    INDEX
    Explanations

    numbers followed by periods

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

    lists of named entities

    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
    ilj
    0.42
     давления
    0.41
    സ
    0.41
     ګ
    0.40
     난
    0.40
     Itália
    0.40
     Biblia
    0.39
    ilizar
    0.39
    𝟏
    0.39
     Га
    0.39
    POSITIVE LOGITS
    ৯৫
    0.45
    মিও
    0.45
     ducks
    0.45
     itself
    0.43
     cohort
    0.43
     eget
    0.43
     centerline
    0.43
    自身的
    0.42
     beque
    0.42
    owns
    0.42
    Activations Density 0.009%

    No Known Activations