© 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. 12385
    Prev
    Next
    INDEX
    Explanations

    reset and reset nothing

    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
    aughan
    -0.79
    གས་
    -0.78
    ाष
    -0.77
     Katowice
    -0.76
     Distribute
    -0.74
     子供
    -0.74
     necesidad
    -0.74
     artific
    -0.74
     Wikime
    -0.72
     Delayed
    -0.72
    POSITIVE LOGITS
     reuse
    1.73
     previous
    1.63
     reset
    1.48
     clean
    1.38
     prior
    1.33
     recycled
    1.31
     recycle
    1.28
     cleared
    1.27
    recycled
    1.26
    previous
    1.23
    Activations Density 0.085%

    No Known Activations