© 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. 77168
    Prev
    Next
    INDEX
    Explanations

    phrases like "a nice" or "are welcome"

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

    explaining obligations and details

    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
    下記の
    0.55
     belir
    0.54
     mevcut
    0.51
     годом
    0.51
    ㎡
    0.50
     hangi
    0.50
     spt
    0.49
     グ
    0.49
     Samo
    0.49
     リュ
    0.48
    POSITIVE LOGITS
    ק
    0.55
    ט
    0.51
    ф
    0.45
    áy
    0.43
    也是
    0.42
    шена
    0.42
    нь
    0.42
    হাব
    0.41
     заслу
    0.41
    奏
    0.41
    Activations Density 0.000%

    No Known Activations