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. 8114
    Prev
    Next
    INDEX
    Explanations

    color codes

    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
     there
    -1.29
     one
    -1.10
    月
    -1.02
     on
    -0.99
     went
    -0.99
     can
    -0.91
     may
    -0.91
    非
    -0.90
     since
    -0.89
     Since
    -0.88
    POSITIVE LOGITS
     MANY
    1.10
    contained
    1.06
    hôpital
    1.03
    rofl
    0.98
    旄
    0.97
    つづく
    0.96
     perdre
    0.96
    congrats
    0.96
     dreary
    0.95
     vibrant
    0.94
    Activations Density 0.004%

    No Known Activations