Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 264
    Prev
    Next
    INDEX
    Explanations

    instructions, drives, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    l
    0.57
    in
    0.51
    de
    0.50
     lifecycle
    0.48
    d
    0.48
     cycle
    0.46
    ih
    0.46
    ing
    0.46
    ,
    0.46
     building
    0.46
    POSITIVE LOGITS
    та
    0.58
    к
    0.58
    клу
    0.57
    слав
    0.56
    стал
    0.55
    м
    0.54
    й
    0.54
    Refrigerator
    0.53
    нца
    0.53
    лав
    0.52
    Activations Density 0.001%

    No Known Activations