© 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. 191519
    Prev
    Next
    INDEX
    Explanations

    offer, brewery, marriage, set

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

    enumeration of specific categories or orders

    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
     geg
    0.49
    шения
    0.48
     berkaitan
    0.43
    elems
    0.42
    e
    0.41
    ورا
    0.40
    ตก
    0.40
    ਥ
    0.40
    ﺜ
    0.40
    waar
    0.40
    POSITIVE LOGITS
     चक्रवृद्धि
    0.52
     পূর্ববাংলার
    0.51
    梩
    0.50
     unsuspecting
    0.47
     Kauff
    0.47
     통
    0.47
     lion
    0.46
     ಎಂಬ
    0.46
     abiding
    0.45
     lepid
    0.45
    Activations Density 0.000%

    No Known Activations