© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54354
    Prev
    Next
    INDEX
    Explanations

    whom the

    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
    esy
    -0.72
     zaken
    -0.71
     artis
    -0.68
    artis
    -0.66
     PAND
    -0.66
     izo
    -0.65
     Mula
    -0.65
    Sitio
    -0.64
    relative
    -0.64
     caractères
    -0.64
    POSITIVE LOGITS
     lockdown
    0.82
     lockdowns
    0.73
    ione
    0.70
     Kauf
    0.67
    ขับ
    0.67
     الو
    0.66
     negotiation
    0.66
     Ruf
    0.65
     Open
    0.65
    arski
    0.64
    Activations Density 0.049%

    No Known Activations