© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 302
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    𒉈
    1.84
    뿯
    1.83
    十伍章
    1.81
     নেতাদের
    1.76
    BUGFS
    1.70
    十玖章
    1.69
    ServiceClient
    1.67
    𒌈
    1.66
    甦
    1.66
     maan
    1.66
    POSITIVE LOGITS
     laws
    1.47
     Laws
    1.44
    法令
    1.32
     relating
    1.32
     Relating
    1.31
    法规
    1.31
    geving
    1.30
     prescribing
    1.29
     regulations
    1.28
     underpinning
    1.23
    Activations Density 2.235%

    No Known Activations