© 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. 85280
    Prev
    Next
    INDEX
    Explanations

    automatically generated

    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
    \
    -3.64
     I
    -3.05
     '
    -3.03
    (
    -2.84
     The
    -2.77
     implication
    -2.45
     lament
    -2.45
     terrific
    -2.38
    爸爸
    -2.36
     !!!!
    -2.33
    POSITIVE LOGITS
    酲
    3.91
    玧
    3.39
    啣
    3.09
    以上です
    3.00
     []
    2.97
    酝
    2.91
    闳
    2.91
    怍
    2.88
    Ꭳ
    2.88
    ouſ
    2.88
    Activations Density 0.014%

    No Known Activations