© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99013
    Prev
    Next
    INDEX
    Explanations

    pronoun acting

    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
     doing
    -0.89
     کنه
    -0.81
     would
    -0.78
    ässä
    -0.77
     Гали
    -0.75
     migliore
    -0.75
    般的
    -0.74
     telling
    -0.73
    INSIDE
    -0.71
     וח
    -0.70
    POSITIVE LOGITS
     pay
    0.93
     assayed
    0.88
     voted
    0.84
     bezahlen
    0.84
    🪞
    0.83
     bargain
    0.81
     Mell
    0.81
    パターン
    0.80
     signé
    0.80
     indescri
    0.79
    Activations Density 0.020%

    No Known Activations