Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 223
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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_34/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
     koruyucu
    -0.85
     memenangkan
    -0.80
     uscire
    -0.80
     váš
    -0.79
    стон
    -0.77
     Ausstellung
    -0.76
    cties
    -0.74
    흩
    -0.74
    Är
    -0.74
     cuerdas
    -0.74
    POSITIVE LOGITS
     asing
    0.82
     Arbit
    0.81
     sorties
    0.79
     bassin
    0.79
     Medea
    0.79
     bair
    0.77
     Gestalt
    0.76
     quên
    0.75
    中野
    0.75
     prosa
    0.74
    Activations Density 0.013%

    No Known Activations