© 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. 128713
    Prev
    Next
    INDEX
    Explanations

    age or duration thresholds

    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
    Lorsque
    -1.51
     was
    -1.37
     lorsque
    -1.32
    ׳
    -1.29
    _{
    -1.28
     подозре
    -1.27
    ப்பட்டது
    -1.27
    万円
    -1.26
    THEY
    -1.23
     delicioso
    -1.23
    POSITIVE LOGITS
     or
    3.34
     from
    1.85
     either
    1.54
     according
    1.48
    ITHER
    1.41
    あるいは
    1.38
    嫉
    1.36
     your
    1.34
     или
    1.33
     hoặc
    1.29
    Activations Density 0.140%

    No Known Activations