© 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. 9638
    Prev
    Next
    INDEX
    Explanations

    La followed by a word

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

    boxed numerical result

    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
     $\
    0.43
    án
    0.42
    声
    0.42
    ões
    0.40
    ers
    0.39
     speck
    0.39
     Inv
    0.38
    pas
    0.37
    alities
    0.37
     Expl
    0.37
    POSITIVE LOGITS
     esso
    0.42
     negra
    0.42
     malah
    0.42
     الجنوبية
    0.42
    +}$
    0.41
    地の
    0.41
    োর্টে
    0.41
     অনুরূপ
    0.40
     térmica
    0.39
     classica
    0.39
    Activations Density 0.046%

    No Known Activations