© 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. 224032
    Prev
    Next
    INDEX
    Explanations

    quarters around

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

    underlying asset or web page

    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
    0.51
    are
    0.47
     incidental
    0.47
     is
    0.46
    j
    0.46
     are
    0.45
    ing
    0.45
    onte
    0.44
    rand
    0.43
    idos
    0.42
    POSITIVE LOGITS
     Cũng
    0.54
     BETTER
    0.49
     এলইডি
    0.48
    পী
    0.48
    蓽
    0.48
     কাপ
    0.48
     単
    0.48
     März
    0.47
    োগ
    0.47
     মডেল
    0.47
    Activations Density 0.001%

    No Known Activations