© 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. 233628
    Prev
    Next
    INDEX
    Explanations

    Factual descriptors or substances

    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
    PhysRev
    0.42
    ^{+}(
    0.41
    edged
    0.41
    ^{+},
    0.39
    叉
    0.39
    ட்ப
    0.38
    где
    0.37
    مارات
    0.37
     TABLE
    0.37
    ibfk
    0.37
    POSITIVE LOGITS
     Kč
    0.52
     പ്രേ
    0.51
     spolupr
    0.50
     बोलेंगे
    0.49
     całkow
    0.48
     गोल्ड
    0.47
     സഹ
    0.47
     hipster
    0.47
    狙
    0.47
     grenade
    0.46
    Activations Density 0.000%

    No Known Activations