© 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. 239628
    Prev
    Next
    INDEX
    Explanations

    DOA / Plate / worst infant / your site

    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
    alist
    0.55
    al
    0.54
    zī
    0.52
    惆
    0.49
    sts
    0.47
    stä
    0.47
    cription
    0.45
    dde
    0.44
    algebra
    0.44
     cardamom
    0.43
    POSITIVE LOGITS
    Decoder
    0.51
    Devil
    0.46
    يفي
    0.45
    Notify
    0.45
     hundreds
    0.43
    ן
    0.43
    SetUp
    0.43
    ブラック
    0.43
     notifying
    0.43
    ு
    0.43
    Activations Density 0.001%

    No Known Activations