© 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. 84476
    Prev
    Next
    INDEX
    Explanations

    call office business phone

    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
     you
    -1.61
     this
    -1.43
     these
    -1.42
     so
    -1.33
     those
    -1.31
     varios
    -1.30
     both
    -1.29
     isso
    -1.28
     inmedi
    -1.27
    hmig
    -1.26
    POSITIVE LOGITS
     to
    2.13
     for
    1.72
     antwoord
    1.70
     illustratie
    1.67
     was
    1.63
     menghadirkan
    1.44
     mendapat
    1.44
     about
    1.41
     ontdek
    1.39
     diinginkan
    1.34
    Activations Density 0.015%

    No Known Activations