© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 250585
    Prev
    Next
    INDEX
    Explanations

    please bring, whole lot

    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
     unequivocally
    0.50
     unlikely
    0.49
     broadly
    0.49
     unsurprisingly
    0.49
     no
    0.46
     scholars
    0.46
    긋
    0.46
     historically
    0.45
     clearly
    0.45
     whether
    0.44
    POSITIVE LOGITS
    ího
    0.47
    譎
    0.46
     बॉल
    0.45
    ফ
    0.44
    aghetti
    0.44
    entrum
    0.43
    omb
    0.43
     প্রথম
    0.43
    ”-
    0.43
    细腻
    0.43
    Activations Density 0.000%

    No Known Activations