© 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. 7314
    Prev
    Next
    INDEX
    Explanations

    knowledge claims

    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
    ís
    2.27
    ͯ
    2.21
    \"
    2.21
    à
    2.20
    ma
    2.09
    ھی
    2.09
    吓
    2.09
    @"
    2.08
    ्रेडिट
    2.06
    Tapi
    2.05
    POSITIVE LOGITS
    a
    3.57
    ン
    3.45
    ו
    3.25
    ে
    3.16
    יא
    3.07
    ه
    3.05
    ați
    3.02
    𝑡
    2.93
    ಿ
    2.92
    ington
    2.89
    Activations Density 0.023%

    No Known Activations