© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12774
    Prev
    Next
    INDEX
    Explanations

    neglect, art, copy, behavior, functioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فقط
    -1.59
     uniquement
    -1.51
    撂
    -1.40
     jabón
    -1.40
     enlever
    -1.39
     การ
    -1.38
    -1.38
     =
    -1.37
     déchets
    -1.36
    commonly
    -1.36
    POSITIVE LOGITS
     with
    2.25
     without
    2.03
     has
    2.00
     by
    1.85
     before
    1.73
    相应的
    1.67
     came
    1.64
     through
    1.60
     while
    1.55
     in
    1.53
    Activations Density 0.113%
    No Known Activations