© 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. 200109
    Prev
    Next
    INDEX
    Explanations

    rubbish bin rental

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

    shadow puppets

    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
     ugljik
    0.50
    ,_-
    0.49
    țele
    0.49
    Misc
    0.49
    ادة
    0.49
    ană
    0.48
    쾨
    0.47
    یدی
    0.47
    italizationType
    0.47
     pdelay
    0.46
    POSITIVE LOGITS
     ダイニング
    0.51
    udian
    0.46
    mejor
    0.46
     Ч
    0.44
     decomposition
    0.44
    unga
    0.44
     л
    0.43
    Y
    0.43
    咱們
    0.42
     ball
    0.41
    Activations Density 0.000%

    No Known Activations