© 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. 557
    Prev
    Next
    INDEX
    Explanations

    .

    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
    ers
    0.83
    -
    0.81
    '
    0.77
    aters
    0.73
    ’
    0.71
    ery
    0.71
    atta
    0.70
    ie
    0.69
    ists
    0.66
     national
    0.66
    POSITIVE LOGITS
    𐰣
    1.29
    𐰃
    1.26
    𐰆
    1.25
    ங்கிணை
    1.23
    Phương
    1.23
    ዖ
    1.22
    Ⲱ
    1.21
    Github
    1.21
    𒁀
    1.20
    𒊑
    1.18
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.