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. 23
    Prev
    Next
    INDEX
    Explanations

    celebrity gossip mentions

    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
     our
    -1.80
     or
    -1.49
     we
    -1.35
     spurred
    -1.24
     might
    -1.23
     perhaps
    -1.13
     first
    -1.13
     nestled
    -1.13
     may
    -1.13
     my
    -1.13
    POSITIVE LOGITS
     eſſ
    1.47
    ├
    1.46
    ['
    1.41
    focused
    1.34
    really
    1.31
    definitely
    1.30
    needed
    1.29
    奁
    1.27
    primarily
    1.27
    totally
    1.27
    Activations Density 0.011%

    No Known Activations