© 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. 117442
    Prev
    Next
    INDEX
    Explanations

    communication and community

    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
    吁
    -0.77
    д
    -0.73
     antigüedad
    -0.71
     fed
    -0.70
    мед
    -0.70
    Sighs
    -0.69
    牝
    -0.69
    Samp
    -0.68
     gegen
    -0.68
     Leben
    -0.68
    POSITIVE LOGITS
     Commun
    0.94
    Commun
    0.83
     resend
    0.81
     smears
    0.79
     COMM
    0.79
     Komunikasi
    0.78
    ocell
    0.77
     COMMUNIC
    0.77
     Communication
    0.76
     harassed
    0.76
    Activations Density 0.019%

    No Known Activations