© 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. 110642
    Prev
    Next
    INDEX
    Explanations

    a piece / each

    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
    Rk
    -0.81
     ACID
    -0.77
    hoedd
    -0.76
     sinner
    -0.76
     sujetos
    -0.76
     squire
    -0.74
    pI
    -0.73
    ਦ
    -0.73
    actually
    -0.73
    แบบ
    -0.73
    POSITIVE LOGITS
     apiece
    3.95
    ずつ
    1.80
    씩
    1.57
     করে
    1.44
     each
    1.32
    ap
    1.28
    づ
    1.27
    ず
    1.17
     ap
    1.12
     Ap
    1.12
    Activations Density 0.036%

    No Known Activations