© 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. 156954
    Prev
    Next
    INDEX
    Explanations

    economical, conditions, communicate, reference

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

    concepts related to days of the week

    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
    接觸
    0.43
    萛
    0.41
    |,
    0.41
     пространства
    0.41
    끗
    0.40
     จริง
    0.40
     закончи
    0.40
    ጀመሪያ
    0.40
    늉
    0.40
     genuinely
    0.40
    POSITIVE LOGITS
    zq
    0.46
     Monday
    0.44
    付き
    0.43
     w
    0.43
     Mondays
    0.42
     Thursday
    0.41
     Kaise
    0.41
     Müdür
    0.41
     eight
    0.40
     kwa
    0.40
    Activations Density 0.001%

    No Known Activations