© 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. 71021
    Prev
    Next
    INDEX
    Explanations

    all the features

    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
     there
    -1.60
     anything
    -1.49
    handedly
    -1.45
     vistas
    -1.45
    、“
    -1.35
    anything
    -1.34
     إليها
    -1.31
     any
    -1.30
    ’)
    -1.29
    ．．
    -1.28
    POSITIVE LOGITS
     of
    1.71
     -
    1.56
    にしても
    1.41
    1
    1.34
    的身
    1.28
    li
    1.27
    v
    1.26
     arbets
    1.22
     other
    1.21
     imperfectly
    1.19
    Activations Density 0.060%

    No Known Activations