© 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. 255
    Prev
    Next
    INDEX
    Explanations

    architectural construction

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     '/'
    0.89
     wi
    0.83
     extraneous
    0.82
     amenable
    0.78
    ه
    0.77
     suppose
    0.76
     deriving
    0.76
     sl
    0.76
     supp
    0.75
     &/
    0.75
    POSITIVE LOGITS
    ómago
    1.38
    ocuk
    1.36
    様専用
    1.19
    ánto
    1.17
    ůj
    1.16
    étera
    1.16
    ifício
    1.15
    comando
    1.15
     deputado
    1.14
    ériences
    1.12
    Activations Density 4.155%

    No Known Activations