© 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. 135546
    Prev
    Next
    INDEX
    Explanations

    day shipping

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

    based on context

    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
    aren
    0.57
    or
    0.54
     equator
    0.54
     tree
    0.53
    ate
    0.51
     mural
    0.51
     u
    0.50
     surrogate
    0.50
    ical
    0.50
     co
    0.50
    POSITIVE LOGITS
    赤ちゃん
    0.58
    Agricult
    0.52
    thisStudent
    0.51
     прият
    0.50
    怠
    0.48
    ब्रा
    0.48
    盻
    0.47
     выполнять
    0.46
     Име
    0.46
    ब्राह
    0.46
    Activations Density 0.000%

    No Known Activations