© 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. 15626
    Prev
    Next
    INDEX
    Explanations

    code comments and professional advice

    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
    ي
    1.64
    ০
    1.46
    ための
    1.35
    ੀ
    1.25
    يلي
    1.24
    ために
    1.20
    ∠
    1.18
    тную
    1.17
    يّ
    1.14
    тні
    1.13
    POSITIVE LOGITS
     refere
    1.47
     మహి
    1.36
    ric
    1.35
    rics
    1.30
     ativa
    1.20
     REFER
    1.20
     hashtags
    1.20
    pyrrolo
    1.20
     Jasper
    1.20
    缈
    1.18
    Activations Density 0.000%

    No Known Activations