© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58936
    Prev
    Next
    INDEX
    Explanations

    numbers and specific words

    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
    הם
    -0.89
     biasanya
    -0.83
    už
    -0.82
    כּ
    -0.82
    всегда
    -0.81
     materiału
    -0.80
     jų
    -0.80
    moc
    -0.80
    cutie
    -0.79
    Marque
    -0.79
    POSITIVE LOGITS
     SIX
    0.88
     DFB
    0.88
    Acti
    0.86
     SEVEN
    0.85
     Genocide
    0.84
     SDGs
    0.84
    没有任何
    0.83
     sieben
    0.83
     IOT
    0.82
    ISIS
    0.82
    Activations Density 0.000%

    No Known Activations