© 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-16K
    7. 11781
    Prev
    Next
    INDEX
    Explanations

    place names and datelines

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

    days of the week and dates

    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_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
     ಚೆ
    0.46
    ్ఞ
    0.46
    aprendizaje
    0.45
    Funcion
    0.41
     एफ
    0.40
     проблем
    0.40
    南海
    0.39
    )$.
    0.39
     प्रॉब्ल
    0.39
     Ramón
    0.39
    POSITIVE LOGITS
     Militia
    0.43
     avail
    0.40
     amplitudes
    0.39
     oper
    0.39
     kı
    0.38
     قنات
    0.38
     Transit
    0.38
     suspe
    0.38
     militia
    0.38
     permukaan
    0.38
    Activations Density 0.027%

    No Known Activations