© 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. 225
    Prev
    Next
    INDEX
    Explanations

    defining identity and development

    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
     masy
    1.96
    ٹر
    1.66
    WILL
    1.62
     ausgel
    1.61
    C
    1.59
    Fl
    1.59
    Lem
    1.56
    B
    1.53
    R
    1.51
    E
    1.51
    POSITIVE LOGITS
     derivative
    1.84
    fileID
    1.81
     Miscellaneous
    1.77
     আগ
    1.70
    ĭ
    1.70
    icarboxylic
    1.69
     MIME
    1.69
     Derivative
    1.69
     prequel
    1.67
     miscellaneous
    1.67
    Activations Density 0.000%

    No Known Activations