© 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. 137005
    Prev
    Next
    INDEX
    Explanations

    saved files, portion of product, modified, limitation

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

    explanation of control and conflict

    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
     tax
    0.49
     hill
    0.46
     mall
    0.45
     た
    0.45
     bamboo
    0.44
     judg
    0.43
     gage
    0.42
     উল্ল
    0.41
     kon
    0.41
     dad
    0.41
    POSITIVE LOGITS
    сні
    0.58
    нем
    0.56
    amai
    0.56
    elbe
    0.52
    рока
    0.49
    сында
    0.48
    ató
    0.48
     лише
    0.48
    𝗁
    0.48
    remos
    0.48
    Activations Density 0.000%

    No Known Activations