© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43186
    Prev
    Next
    INDEX
    Explanations

    separator or month abbreviation

    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
    
    -3.41
    镭
    -3.36
    ſam
    -3.06
    餽
    -3.02
    忖
    -2.91
     myſelf
    -2.91
    錒
    -2.83
    攆
    -2.80
    เกง
    -2.78
     to
    -2.75
    POSITIVE LOGITS
    9
    5.84
    4
    5.75
    2
    5.63
    6
    5.34
    7
    5.31
    5
    5.22
    8
    4.91
    3
    4.84
    1
    4.69
    If
    3.75
    Activations Density 0.002%

    No Known Activations