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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2552
    Prev
    Next
    INDEX
    Explanations

    doux

    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
    м
    1.69
    layered
    1.53
    ეგისტრ
    1.50
    加坡
    1.49
    moniker
    1.48
    <unused313>
    1.47
     affluent
    1.47
    branched
    1.42
    ваи
    1.42
     使っ
    1.41
    POSITIVE LOGITS
    라고
    1.19
    erek
    1.16
    c
    1.15
    ku
    1.13
     phí
    1.10
    chen
    1.10
    ’
    1.10
    P
    1.10
    ľa
    1.08
    ).
    1.07
    Activations Density 0.169%

    No Known Activations