© 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. 32924
    Prev
    Next
    INDEX
    Explanations

    context for qualifiers

    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
     решений
    0.48
    复杂度
    0.48
    ekyll
    0.46
    风险
    0.45
    ט
    0.45
    ᑦ
    0.44
     รวมถึง
    0.44
    Դ
    0.44
    ɮ
    0.43
    fqsen
    0.43
    POSITIVE LOGITS
    것도
    0.40
     unemployed
    0.40
     watert
    0.39
     것도
    0.38
     endow
    0.38
     yü
    0.38
     loaf
    0.38
     তিনিও
    0.38
     another
    0.37
     másik
    0.37
    Activations Density 0.018%

    No Known Activations