© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28358
    Prev
    Next
    INDEX
    Explanations

    payloads, mining, transmissions, molecules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     letzte
    0.51
    t
    0.50
    ayn
    0.49
    d
    0.49
    nd
    0.49
    olm
    0.48
    umen
    0.47
    graph
    0.47
    eri
    0.47
    g
    0.47
    POSITIVE LOGITS
    يزات
    0.48
     SCAN
    0.44
    物を
    0.41
     породы
    0.41
    物の
    0.41
     частично
    0.40
     повинні
    0.39
     worden
    0.39
     marginally
    0.39
     impor
    0.38
    Activations Density 0.002%

    No Known Activations