© 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. 40-GEMMASCOPE-2-RES-262K
    7. 84308
    Prev
    Next
    INDEX
    Explanations

    authorization texts

    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_40_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
    茘
    0.40
     являются
    0.39
    ází
    0.38
     Beatles
    0.38
     всей
    0.37
     এক্সপ্রেস
    0.36
     Greatest
    0.36
    漓
    0.36
     Shab
    0.36
    หมือน
    0.35
    POSITIVE LOGITS
     autorisation
    0.42
     authorization
    0.39
     hes
    0.39
    ROE
    0.39
     kane
    0.39
     authorisation
    0.38
    authorization
    0.37
    ichni
    0.36
    投資
    0.36
     nigeria
    0.36
    Activations Density 0.000%

    No Known Activations