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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118681
    Prev
    Next
    INDEX
    Explanations

    events and states happening

    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
     بودند
    -0.91
     sıra
    -0.84
    することができます
    -0.81
    🏿
    -0.81
     때문에
    -0.78
    WindowListener
    -0.78
    альных
    -0.78
     рослин
    -0.77
    そうだ
    -0.76
     trabajó
    -0.76
    POSITIVE LOGITS
     occurs
    2.73
     odby
    2.72
     انجام
    2.45
     erfolgt
    2.44
     occur
    2.39
     avviene
    2.38
     dilakukan
    2.31
     відбу
    2.30
     happens
    2.27
     happen
    2.23
    Activations Density 0.049%

    No Known Activations