© 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. 68387
    Prev
    Next
    INDEX
    Explanations

    common phrases after certain words

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

    monitoring, protect, efficiency, lack

    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
    कट
    0.51
    ཋ
    0.49
    Kako
    0.48
    Funeral
    0.48
    Oste
    0.47
    קט
    0.46
    harth
    0.46
    Hak
    0.45
    뻣
    0.45
    힛
    0.45
    POSITIVE LOGITS
     failure
    0.54
     ä
    0.52
     hundred
    0.49
     ร้อย
    0.49
     point
    0.49
     書き
    0.46
     location
    0.46
     製
    0.45
     supplied
    0.45
     ignoring
    0.45
    Activations Density 0.000%

    No Known Activations