© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110592
    Prev
    Next
    INDEX
    Explanations

    superlative comparison to nouns

    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
     of
    -2.13
     part
    -1.50
     things
    -1.27
     among
    -1.13
     thing
    -1.12
     parts
    -1.05
     aspect
    -1.01
    دارد
    -0.99
     persons
    -0.97
     portion
    -0.95
    POSITIVE LOGITS
     selves
    1.13
     assets
    1.12
     asset
    1.09
    !");
    1.02
     работе
    1.01
     beiden
    1.00
     hacer
    0.98
    opropyl
    0.93
     accomplishments
    0.91
    朋友
    0.91
    Activations Density 0.033%

    No Known Activations