© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11044
    Prev
    Next
    INDEX
    Explanations

    SvelteKit

    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
    ’
    1.36
     literally
    1.22
    '
    1.20
    ʼ
    1.06
    ′
    1.00
    arelli
    0.99
     gives
    0.93
     purposefully
    0.92
     actually
    0.92
    ürn
    0.88
    POSITIVE LOGITS
    ඪ
    1.18
    Descripcion
    1.18
    Limite
    1.11
    Birth
    1.10
    Latency
    1.09
    لى
    1.09
    Sending
    1.09
    Reduced
    1.09
    Attrition
    1.08
    Deleting
    1.07
    Activations Density 0.020%

    No Known Activations