© 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. 43
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and durations

    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
    o
    2.35
    ে
    2.15
    oC
    2.11
    oop
    1.99
    er
    1.83
    a
    1.82
    surprisingly
    1.82
    e
    1.81
    ি
    1.81
    verick
    1.77
    POSITIVE LOGITS
    έλ
    1.79
     verte
    1.76
    gı
    1.60
     ಸಾಧ್ಯ
    1.55
     mej
    1.48
     umiejęt
    1.47
    uchi
    1.45
    elerini
    1.44
    Interpret
    1.44
    ρίας
    1.44
    Activations Density 0.000%

    No Known Activations