© 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. 12330
    Prev
    Next
    INDEX
    Explanations

    mechanisms and effects

    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
     to
    -0.94
    apore
    -0.92
    ursor
    -0.91
     repercussions
    -0.90
    ₤
    -0.88
     Implications
    -0.88
     consequ
    -0.85
     Sólo
    -0.85
    WithTag
    -0.84
     замет
    -0.82
    POSITIVE LOGITS
     such
    1.03
     primarily
    0.99
     include
    0.93
     lidé
    0.93
     are
    0.93
     Konzentration
    0.92
     bolí
    0.92
     explanation
    0.91
     explain
    0.90
     explained
    0.90
    Activations Density 0.126%

    No Known Activations