© 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. 22-GEMMASCOPE-RES-131K
    7. 12228
    Prev
    Next
    INDEX
    Explanations

    together, mutually, between

    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
     and
    -1.38
    kih
    -0.94
     sayfası
    -0.88
     whilst
    -0.88
     problemen
    -0.84
    Câ
    -0.82
     contient
    -0.81
    而
    -0.79
    kuli
    -0.79
    ichtete
    -0.79
    POSITIVE LOGITS
     are
    2.25
     have
    1.65
     arasındaki
    1.42
     were
    1.39
     together
    1.34
     között
    1.31
     mutually
    1.28
     gemens
    1.23
    Together
    1.21
     can
    1.15
    Activations Density 0.107%

    No Known Activations