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. 110218
    Prev
    Next
    INDEX
    Explanations

    has called

    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
     such
    -1.25
    =?";
    -1.00
    IFORM
    -0.99
    Kesimpulan
    -0.98
     LIABLE
    -0.91
    atase
    -0.91
    ++,
    -0.90
     МВД
    -0.88
     ";
    -0.87
    ;*/
    -0.87
    POSITIVE LOGITS
    tvrt
    0.90
     souple
    0.90
    éfonos
    0.89
     Newly
    0.89
     여
    0.88
     has
    0.87
    号線
    0.86
    Sek
    0.85
     SPOILER
    0.82
    େ
    0.82
    Activations Density 0.024%

    No Known Activations