© 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. 11489
    Prev
    Next
    INDEX
    Explanations

    boolean or keyword followed by punctuation

    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
     about
    -1.09
    _
    -1.08
     was
    -1.07
     ensured
    -1.00
    /
    -0.99
     intended
    -0.98
     These
    -0.92
    :
    -0.91
     is
    -0.90
     mantuvo
    -0.89
    POSITIVE LOGITS
     sytuacji
    1.10
     secretario
    1.04
     Quiero
    1.03
    vč
    1.02
     DÍA
    1.02
     queijo
    1.01
    jącą
    1.01
     manteau
    1.01
     možnosti
    0.99
    ashions
    0.99
    Activations Density 0.001%

    No Known Activations