Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 288
    Prev
    Next
    INDEX
    Explanations

    Chabad and Hebrew

    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
    indeer
    -0.89
    が
    -0.88
     caz
    -0.79
     Koo
    -0.72
     io
    -0.71
     carne
    -0.71
     Placement
    -0.71
    柑
    -0.71
    博物館
    -0.70
     persiapan
    -0.70
    POSITIVE LOGITS
    事で
    0.99
    為に
    0.92
    Exactly
    0.88
    Either
    0.85
    Decided
    0.84
    ウェット
    0.84
     اتصال
    0.83
     câmbio
    0.83
     spake
    0.82
     támogat
    0.82
    Activations Density 0.019%

    No Known Activations