© 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. 15484
    Prev
    Next
    INDEX
    Explanations

    comment markers and code structure

    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
    mon
    0.50
    plate
    0.49
    comm
    0.49
    C
    0.49
     l
    0.48
    icated
    0.48
     i
    0.48
    ↵
    0.48
    inn
    0.47
    R
    0.46
    POSITIVE LOGITS
     BVHTree
    0.53
     armes
    0.53
    énagement
    0.52
     CORPER
    0.51
     BLUENRG
    0.50
     محاسبه
    0.49
    鷸
    0.48
     nhiễm
    0.48
    ніх
    0.48
    沩
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.