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. 8456
    Prev
    Next
    INDEX
    Explanations

    striking descriptive adjectives

    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
     on
    -2.19
     in
    -2.16
     at
    -1.99
     took
    -1.94
     came
    -1.88
     went
    -1.87
     get
    -1.85
     from
    -1.84
     or
    -1.82
     all
    -1.80
    POSITIVE LOGITS
     myriad
    2.05
     quintessential
    1.90
     acclaimed
    1.89
     revamped
    1.89
     ridiculously
    1.88
     wacky
    1.86
     strikingly
    1.84
     colossal
    1.81
     shimmering
    1.81
     insanely
    1.78
    Activations Density 0.008%

    No Known Activations