© 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. 31-GEMMASCOPE-2-RES-262K
    7. 62516
    Prev
    Next
    INDEX
    Explanations

    long stretch

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

    contraction due to

    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_31_width_262k_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
    めでとう
    0.48
    Interfaz
    0.48
    бки
    0.47
    мета
    0.47
     анализа
    0.46
    轺
    0.46
    灝
    0.46
    攝影
    0.45
     ಎರಡು
    0.45
    фик
    0.45
    POSITIVE LOGITS
     quedó
    0.49
     naturellement
    0.48
     quedaron
    0.48
    shire
    0.47
     mue
    0.46
     miała
    0.46
    cn
    0.45
    list
    0.44
    tea
    0.44
    aro
    0.43
    Activations Density 0.000%

    No Known Activations