© 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. 174608
    Prev
    Next
    INDEX
    Explanations

    then, need, later, when, not

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

    multilingual introductions

    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
    chens
    0.47
     Upon
    0.46
    த்தி
    0.45
    Will
    0.40
     Wel
    0.40
    част
    0.40
    ഷ
    0.40
     Phillips
    0.38
     Wil
    0.38
    Video
    0.38
    POSITIVE LOGITS
     도입
    0.47
    就需要
    0.47
     забы
    0.46
    으니까
    0.46
     nöt
    0.45
    忘了
    0.45
    辽
    0.43
     पहले
    0.43
    (=
    0.43
     Тогда
    0.42
    Activations Density 0.002%

    No Known Activations