© 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. 14236
    Prev
    Next
    INDEX
    Explanations

    local imports

    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
    andang
    2.62
    েনারেল
    2.62
    َّا
    2.56
     εί
    2.51
    ное
    2.47
    Ist
    2.41
    ‬‬
    2.36
    ⮚
    2.36
    ्रेडिट
    2.32
    &#
    2.31
    POSITIVE LOGITS
    onnay
    3.18
    amana
    2.95
    NonNull
    2.89
    amask
    2.82
    сибо
    2.78
     Roskov
    2.74
    鹉
    2.73
    س
    2.71
     peroxidase
    2.68
    اك
    2.67
    Activations Density 0.030%

    No Known Activations