© 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. 39782
    Prev
    Next
    INDEX
    Explanations

    Match

    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
    '
    -3.94
    1
    -3.81
    5
    -3.56
     .
    -3.52
    "
    -3.50
    4
    -3.48
    3
    -3.41
    :
    -3.16
     
    -3.13
    6
    -3.06
    POSITIVE LOGITS
    er
    6.53
    ه
    4.78
    zelfde
    3.64
    ে
    3.56
    ו
    3.52
    ு
    3.34
    erl
    3.28
    irmanship
    3.23
    erintah
    3.06
     collectons
    3.06
    Activations Density 0.029%

    No Known Activations