© 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. 84058
    Prev
    Next
    INDEX
    Explanations

    names, information, URL

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

    stories about

    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
    iye
    0.46
    7
    0.44
    ipl
    0.42
    elt
    0.42
    
    0.41
     chirurg
    0.41
    _
    0.40
    limit
    0.40
     crude
    0.40
    Incorrect
    0.40
    POSITIVE LOGITS
     giờ
    0.52
    وں
    0.52
    栆
    0.49
    বাহী
    0.46
     thủy
    0.46
    ängen
    0.46
    นั้น
    0.45
    묘
    0.45
    婍
    0.44
    वेग
    0.43
    Activations Density 0.000%

    No Known Activations