© 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. 1880
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

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

    explaining aspects or options

    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
    逦
    0.53
     பிரச்
    0.50
    ȏ
    0.50
     परसेंटेज
    0.49
    setPassword
    0.48
     धोखाध
    0.48
     רו
    0.47
     उपहार
    0.47
     cliche
    0.46
    릇
    0.46
    POSITIVE LOGITS
     assigns
    0.52
    ioen
    0.49
    َل
    0.49
     ted
    0.48
    وقال
    0.48
     heterod
    0.47
    ')",
    0.46
    ول
    0.45
     eyelids
    0.45
    Arrange
    0.45
    Activations Density 0.000%

    No Known Activations