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. 8628
    Prev
    Next
    INDEX
    Explanations

    by no means

    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
    ónimo
    -0.81
    setto
    -0.81
    curso
    -0.81
    lebih
    -0.81
     MethodInfo
    -0.80
    tuigen
    -0.75
     APPEAL
    -0.74
    Tahun
    -0.73
     Stateful
    -0.73
     grö
    -0.73
    POSITIVE LOGITS
     means
    2.22
    means
    1.77
     stretch
    1.45
     Means
    1.41
    Means
    1.27
     MEANS
    1.22
     означает
    1.16
     mean
    1.13
    stretch
    1.13
     bedeutet
    1.12
    Activations Density 0.008%

    No Known Activations