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. 8694
    Prev
    Next
    INDEX
    Explanations

    Angular lifecycle and components

    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
    Hein
    -0.79
     rose
    -0.79
    uom
    -0.75
     Vad
    -0.73
    Heal
    -0.72
    היו
    -0.67
     victory
    -0.66
     Soc
    -0.66
     vittoria
    -0.66
     Hin
    -0.65
    POSITIVE LOGITS
     ng
    1.12
    ngOn
    1.08
    Changes
    1.06
     lifecycle
    1.00
    Lifecycle
    0.99
     changes
    0.96
    changes
    0.95
     Lifecycle
    0.95
     Changes
    0.84
    lifecycle
    0.84
    Activations Density 0.016%

    No Known Activations