© 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. 12290
    Prev
    Next
    INDEX
    Explanations

    state of the art

    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
    pography
    -1.84
    ícias
    -1.82
    
    -1.69
     LIABLE
    -1.65
    vább
    -1.65
    ulitis
    -1.59
    焢
    -1.59
    aneity
    -1.53
    felizmente
    -1.52
    ograft
    -1.43
    POSITIVE LOGITS
    為に
    1.41
    様な
    1.41
     ennen
    1.30
     erila
    1.25
     trong
    1.22
    {
    1.21
    ようになった
    1.20
     Eighteen
    1.15
     tutkim
    1.15
     yksi
    1.13
    Activations Density 0.036%

    No Known Activations