© 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. 59367
    Prev
    Next
    INDEX
    Explanations

    special characters and foreign words

    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
    
    -2.98
    ſſen
    -2.86
    felpa
    -2.73
    หรือ
    -2.66
     czarna
    -2.55
    驺
    -2.45
    螅
    -2.44
    ⚊
    -2.39
    艫
    -2.36
    絝
    -2.36
    POSITIVE LOGITS
    2
    3.41
    Our
    3.27
    The
    3.11
    '
    3.08
    5
    3.05
    9
    3.00
    You
    2.92
    7
    2.89
    What
    2.89
    O
    2.88
    Activations Density 0.001%

    No Known Activations