© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 37790
    Prev
    Next
    INDEX
    Explanations

    disagreement or negation

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

    crucial / importance

    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
     swoich
    0.49
     kies
    0.42
     corrupt
    0.41
    า
    0.41
     o
    0.41
     i
    0.41
     moulds
    0.41
     ਆਪਣੇ
    0.40
    ﺰ
    0.40
     manipulate
    0.40
    POSITIVE LOGITS
     değil
    0.52
    不是
    0.49
     नहीं
    0.46
     plutôt
    0.46
     दिखी
    0.46
    क्षिप्त
    0.46
     కాదు
    0.44
    缤
    0.44
    rather
    0.44
     героев
    0.43
    Activations Density 0.000%

    No Known Activations