© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10466
    Prev
    Next
    INDEX
    Explanations

    scores and statistics

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

    currency codes like CHF

    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
    നി
    0.42
     dih
    0.39
    ニ
    0.38
     دارو
    0.38
                               
    0.38
     воспа
    0.37
    慢性
    0.36
    存于互联网档案馆
    0.36
    所述
    0.36
     wv
    0.35
    POSITIVE LOGITS
     Grant
    0.44
     }$
    0.42
     Drill
    0.42
    executeQuery
    0.41
     Jac
    0.41
    ques
    0.40
     GY
    0.40
     Gy
    0.39
    ense
    0.38
    itemId
    0.38
    Activations Density 0.014%

    No Known Activations