© 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. 158032
    Prev
    Next
    INDEX
    Explanations

    during tax season

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

    concentration, trade, however, memory, power

    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
    繭
    0.47
    蘭
    0.44
     이러한
    0.43
    顆
    0.42
    結合
    0.41
    譜
    0.41
     אנ
    0.41
    磚
    0.41
    жет
    0.41
    ्रेडिट
    0.41
    POSITIVE LOGITS
     Namespace
    0.53
    TOD
    0.47
     grounding
    0.46
     Verizon
    0.46
     waterways
    0.45
     টিক
    0.45
    RA
    0.44
     Goods
    0.44
     reservados
    0.44
    namespace
    0.43
    Activations Density 0.000%

    No Known Activations