© 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. 57851
    Prev
    Next
    INDEX
    Explanations

    reporting phone calls

    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
     elke
    -0.85
     Bruxelles
    -0.81
    whelming
    -0.81
     masker
    -0.80
     oktober
    -0.79
    ++;
    -0.79
    さも
    -0.79
    ﻧ
    -0.79
     parall
    -0.79
     laver
    -0.79
    POSITIVE LOGITS
     by
    2.47
     phone
    1.92
     telephone
    1.82
     from
    1.71
     during
    1.61
    电话
    1.46
     recently
    1.45
    電話
    1.33
    By
    1.32
     in
    1.23
    Activations Density 0.017%

    No Known Activations