© 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. 38230
    Prev
    Next
    INDEX
    Explanations

    buying, buy, or answered

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

    access, answer, explore, download

    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
     कार्यकर्ते
    0.43
     ஊக்கு
    0.42
     म्हणूनच
    0.41
     ++;
    0.40
    鼓励
    0.39
     Assessment
    0.39
    陞
    0.39
     Fixed
    0.38
     Campaigns
    0.38
     দয়া
    0.38
    POSITIVE LOGITS
    на
    0.48
     audioElement
    0.46
     downsides
    0.45
    ли
    0.44
    噙
    0.44
     FaceTime
    0.43
    秕
    0.43
     beantwort
    0.42
     answered
    0.42
    answ
    0.41
    Activations Density 0.000%

    No Known Activations