© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 135952
    Prev
    Next
    INDEX
    Explanations

    encourage us to improve licensing

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

    providing options and assistance

    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
    actual
    0.49
     Rancho
    0.48
     कि
    0.45
     ເ
    0.45
     பாதுகாப்பு
    0.45
    operational
    0.45
     чем
    0.45
     आराम
    0.44
     задачу
    0.44
     സേ
    0.44
    POSITIVE LOGITS
    γν
    0.48
     étrangères
    0.47
    釧
    0.45
     birefringence
    0.45
     takeover
    0.44
     waveguide
    0.44
     europäischen
    0.44
     tetragonal
    0.44
     Checkout
    0.43
    逡
    0.43
    Activations Density 0.001%

    No Known Activations