© 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. 44890
    Prev
    Next
    INDEX
    Explanations

    graduated from, young children, placed on

    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
     also
    -1.88
     también
    -1.78
     from
    -1.64
     również
    -1.51
     will
    -1.49
     також
    -1.42
     também
    -1.39
    يئة
    -1.37
     cũng
    -1.36
     भी
    -1.36
    POSITIVE LOGITS
    not
    1.52
    no
    1.50
    '
    1.38
     something
    1.38
    U
    1.38
    real
    1.36
    me
    1.33
    I
    1.30
     ">
    1.28
     everything
    1.27
    Activations Density 0.124%

    No Known Activations