© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9888
    Prev
    Next
    INDEX
    Explanations

    kind of

    np_acts-logits-general · gemini-2.5-flash-lite

    dough mixing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    afin
    0.41
    ↕
    0.40
    的不同
    0.39
     телефону
    0.38
     উঠ
    0.38
    DFC
    0.38
    apj
    0.38
    নীয়
    0.37
     دف
    0.37
    ⠀⠀
    0.37
    POSITIVE LOGITS
    abbage
    0.42
    うん
    0.39
    社區
    0.39
     Armen
    0.38
    ெமி
    0.38
    ಸ್ಟ್
    0.37
     बाधित
    0.37
     Nagar
    0.36
    ్రీన్
    0.36
     Breast
    0.36
    Activations Density 0.031%

    No Known Activations