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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7941
    Prev
    Next
    INDEX
    Explanations

    John Scalzi, Joe Avati, SXSW, Invisible Library

    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
     enchufe
    -0.74
     Fury
    -0.72
     fury
    -0.70
     egyszerű
    -0.68
     dyn
    -0.68
    otypic
    -0.67
    Dyn
    -0.66
     DK
    -0.66
     mutant
    -0.65
     currentUser
    -0.65
    POSITIVE LOGITS
    itunes
    0.83
    Rusia
    0.75
     letech
    0.75
    鈣
    0.72
     Vera
    0.71
     Gideon
    0.71
    ⎤
    0.70
    児島
    0.69
     Nome
    0.68
     speciale
    0.68
    Activations Density 0.024%

    No Known Activations