© 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-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2678
    Prev
    Next
    INDEX
    Explanations

    control flow blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     actionable
    0.60
    意見
    0.59
    खम
    0.58
     beam
    0.58
    同志
    0.57
     विषया
    0.57
    -_-
    0.57
    ="-
    0.56
     内容
    0.56
    せい
    0.55
    POSITIVE LOGITS
     realize
    1.42
     realise
    1.28
     realizes
    1.28
     effectively
    1.23
     effectually
    1.19
    更好的
    1.17
    有效地
    1.17
     realises
    1.17
    實現
    1.17
     realizing
    1.16
    Activations Density 0.085%

    No Known Activations