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. 170
    Prev
    Next
    INDEX
    Explanations

    repeated 'a' or 'A' sequences

    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
    guigu
    -1.03
     Later
    -0.86
     later
    -0.86
    insee
    -0.85
    назна
    -0.81
     後
    -0.81
    logitech
    -0.79
    geox
    -0.79
    romolecules
    -0.79
    сное
    -0.78
    POSITIVE LOGITS
     batteries
    1.06
    e
    1.02
    CardContent
    0.91
    as
    0.85
    nativeElement
    0.81
    amię
    0.79
     aaa
    0.79
    强度
    0.78
    Batteries
    0.77
    her
    0.77
    Activations Density 0.022%

    No Known Activations