© 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. 118761
    Prev
    Next
    INDEX
    Explanations

    requiring insurers, with preexisting, from birth

    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
     hurry
    -0.80
     cooked
    -0.77
    magin
    -0.72
     cucchiaio
    -0.72
     initView
    -0.71
     timed
    -0.71
     transport
    -0.71
    HeaderView
    -0.69
    Bacon
    -0.69
     confronted
    -0.68
    POSITIVE LOGITS
    AtIndexPath
    0.84
    esh
    0.83
    ISSION
    0.74
     corrector
    0.74
    ремен
    0.74
     металли
    0.73
    mesh
    0.70
     PEDRO
    0.70
     жі
    0.70
     ─
    0.70
    Activations Density 0.015%

    No Known Activations