© 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. 13-GEMMASCOPE-2-RES-16K
    7. 15500
    Prev
    Next
    INDEX
    Explanations

    huge range

    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_13_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
    </strong>
    1.10
    ol
    1.09
    <em>
    1.08
    ed
    1.05
    iq
    1.04
    es
    1.01
    eng
    1.01
    y
    1.00
    am
    1.00
    m
    0.99
    POSITIVE LOGITS
     थरूर
    1.60
     secretos
    1.55
     Beberapa
    1.50
     zvuk
    1.47
     ਲ
    1.47
    जवळ
    1.46
     médiocrement
    1.43
    只好
    1.42
     अराउंड
    1.42
     बायोलॉजी
    1.40
    Activations Density 0.003%

    No Known Activations