© 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. 34-GEMMASCOPE-RES-131K
    7. 31202
    Prev
    Next
    INDEX
    Explanations

    you followed by auxiliary verbs

    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_34/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
     può
    -1.71
     может
    -1.62
     welches
    -1.41
     graciosos
    -1.38
     HAS
    -1.37
     می‌تواند
    -1.33
     unserer
    -1.32
     NEEDS
    -1.32
     is
    -1.30
     namorados
    -1.30
    POSITIVE LOGITS
     are
    5.31
     have
    3.25
     were
    2.89
     aren
    2.34
     yourself
    2.05
     weren
    1.89
     don
    1.87
    ’
    1.83
     haven
    1.74
    mathrm
    1.66
    Activations Density 0.152%

    No Known Activations