© 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. 246106
    Prev
    Next
    INDEX
    Explanations

    followed by preposition or punctuation

    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
    否
    0.48
     therapeut
    0.42
    Optimization
    0.42
    +)
    0.41
     siap
    0.41
     robbers
    0.40
     GOP
    0.40
    ی
    0.40
    uhi
    0.40
    th
    0.39
    POSITIVE LOGITS
     ['<%=
    0.53
    róleo
    0.50
     fieldContext
    0.49
    mediaDevices
    0.49
     постоян
    0.48
    ্যারি
    0.48
    ageo
    0.48
    杫
    0.47
     agrícola
    0.47
    νη
    0.47
    Activations Density 0.001%

    No Known Activations