© 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. 21210
    Prev
    Next
    INDEX
    Explanations

    money administration

    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
    -3.72
    8
    -3.27
    4
    -3.17
    7
    -3.08
    There
    -3.08
    1
    -2.94
    5
    -2.88
    3
    -2.78
    6
    -2.77
    ’
    -2.59
    POSITIVE LOGITS
     frontières
    2.39
     hefty
    2.27
     them
    2.20
     italianos
    2.20
    他就
    2.19
     revered
    2.16
     dirigentes
    2.16
    ཥ
    2.13
     said
    2.08
     enorme
    2.08
    Activations Density 0.028%

    No Known Activations