© 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. 110465
    Prev
    Next
    INDEX
    Explanations

    Hel followed by ton or der or n or ha or min or ish or low

    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
    ropriate
    -0.83
    acamole
    -0.75
    🕋
    -0.74
     podrán
    -0.73
     początku
    -0.70
    汜
    -0.69
     yapılan
    -0.68
     nutric
    -0.66
     două
    -0.66
     ナビ
    -0.65
    POSITIVE LOGITS
    訶
    0.89
     roads
    0.84
    razione
    0.81
    zungs
    0.81
     road
    0.80
     circus
    0.78
    ченко
    0.77
    led
    0.77
    kingen
    0.76
     Tenggara
    0.75
    Activations Density 0.031%

    No Known Activations