© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118625
    Prev
    Next
    INDEX
    Explanations

    iOS UI view controllers and collections

    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
     all
    -0.87
     did
    -0.86
     primer
    -0.80
    なので
    -0.79
    痣
    -0.76
     didReceive
    -0.74
    ,\
    -0.73
     sudden
    -0.73
    odes
    -0.72
     start
    -0.71
    POSITIVE LOGITS
     ウエスト
    0.90
     Recycle
    0.84
     coûts
    0.82
     geloof
    0.81
     UID
    0.81
     اهم
    0.81
     obicei
    0.80
     Valorant
    0.80
     FOREVER
    0.79
     déplacements
    0.77
    Activations Density 0.040%

    No Known Activations