© 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. 16060
    Prev
    Next
    INDEX
    Explanations

    timeline and quantity

    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
     BONDS
    1.31
     reff
    1.23
     зам
    1.21
    વ
    1.18
     Bonds
    1.14
     Фи
    1.11
     数
    1.11
     го
    1.11
     bertahan
    1.10
    粘
    1.10
    POSITIVE LOGITS
    Ὅ
    1.36
    svelte
    1.28
    addressed
    1.21
     inscribed
    1.19
    ἧ
    1.19
    Ģ
    1.19
    스러
    1.19
    ān
    1.18
    Minute
    1.18
    ὥ
    1.17
    Activations Density 0.000%

    No Known Activations