© 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. 74376
    Prev
    Next
    INDEX
    Explanations

    winter months

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

    ocean and waves

    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
    o
    0.48
    IE
    0.45
     окончания
    0.44
     empl
    0.44
     aşağıdaki
    0.44
    VITY
    0.44
    GP
    0.43
    ("/
    0.43
    NST
    0.43
     oblast
    0.41
    POSITIVE LOGITS
    只会
    0.52
     সর্বদা
    0.49
     항상
    0.47
     पीड़ित
    0.47
     Juventus
    0.46
     तालि
    0.46
     किरदार
    0.45
    ής
    0.45
     ஜோ
    0.45
     গর্ব
    0.45
    Activations Density 0.002%

    No Known Activations