© 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. 5898
    Prev
    Next
    INDEX
    Explanations

    database services

    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
     horrific
    0.55
     hideous
    0.54
     violent
    0.51
     prostitute
    0.50
    レ
    0.50
     terrifying
    0.50
     horr
    0.49
     mystical
    0.48
    ｳ
    0.48
     lawn
    0.48
    POSITIVE LOGITS
     Abbreviations
    0.55
     कार्य
    0.54
    kins
    0.50
    inar
    0.48
     Subsidi
    0.48
     nota
    0.47
     Workshop
    0.47
    ments
    0.46
    Component
    0.46
    Note
    0.46
    Activations Density 0.001%

    No Known Activations