© 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-65K
    7. 64666
    Prev
    Next
    INDEX
    Explanations

    simple observation

    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_65k_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
    MktCap
    0.55
    Mfg
    0.51
    сения
    0.50
    ব্রিটিশ
    0.50
    Gesellschaft
    0.50
    Leben
    0.49
    ⵉ
    0.48
    Arizona
    0.48
    Wert
    0.48
     簡単
    0.47
    POSITIVE LOGITS
     ICT
    0.52
     data
    0.49
     handouts
    0.49
     instrument
    0.44
     Coupled
    0.42
     Museum
    0.42
     Suspension
    0.40
     $\
    0.39
     Academic
    0.39
     Assessments
    0.39
    Activations Density 0.019%

    No Known Activations