© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 873
    Prev
    Next
    INDEX
    Explanations

    numbers and identifiers

    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
    northern
    0.90
    ᒪ
    0.85
    tidy
    0.84
    decomposition
    0.83
    setosa
    0.81
    此之外
    0.81
    className
    0.80
    moderate
    0.78
    hopefully
    0.78
    𝒂
    0.77
    POSITIVE LOGITS
    iel
    0.84
     Pro
    0.80
    als
    0.79
    -
    0.78
     and
    0.76
    )
    0.75
    asi
    0.75
    .
    0.73
    ियों
    0.71
    ).
    0.70
    Activations Density 0.566%

    No Known Activations