Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11626
    Prev
    Next
    INDEX
    Explanations

    always

    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_22/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
     geringe
    -1.05
     soprattutto
    -1.02
     unimagin
    -1.02
    烘
    -1.01
    according
    -1.00
    ㄨ
    -0.99
    恭喜
    -0.99
    mainly
    -0.98
    specifically
    -0.98
     modifié
    -0.95
    POSITIVE LOGITS
     if
    1.20
     therefore
    1.18
     so
    1.16
     ALWAYS
    1.13
     always
    1.13
     поэтому
    1.05
     for
    1.02
     when
    0.98
     only
    0.93
     ensures
    0.92
    Activations Density 0.050%

    No Known Activations