© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9396
    Prev
    Next
    INDEX
    Explanations

    topic starters and questions

    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
    ↵↵
    -2.02
    на
    -1.77
     was
    -1.60
    atação
    -1.55
    сон
    -1.52
    also
    -1.48
     escritora
    -1.46
    on
    -1.45
    ного
    -1.45
    ziała
    -1.43
    POSITIVE LOGITS
     as
    1.87
    뿅
    1.65
     mogę
    1.63
     powin
    1.59
    hamburg
    1.58
     different
    1.58
     REGARD
    1.58
    Библи
    1.58
     mogen
    1.54
    するには
    1.52
    Activations Density 0.000%

    No Known Activations