© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102687
    Prev
    Next
    INDEX
    Explanations

    completion of words and phrases

    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
     "
    -2.42
     '
    -2.20
     devido
    -1.93
    "?
    -1.90
     деца
    -1.84
     alrededores
    -1.81
    被他
    -1.77
    也得
    -1.77
    șe
    -1.76
    都不能
    -1.73
    POSITIVE LOGITS
    ’
    2.39
    when
    2.28
    I
    2.19
    what
    2.17
    When
    2.11
    You
    2.11
    是個
    1.95
    ２
    1.87
    欸
    1.84
    _
    1.81
    Activations Density 0.000%

    No Known Activations