© 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. 16-GEMMASCOPE-2-RES-262K
    7. 86785
    Prev
    Next
    INDEX
    Explanations

    leaving Enron > behind

    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_16_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
    ON
    0.89
    UN
    0.87
    US
    0.84
    E
    0.84
    ANG
    0.84
    CO
    0.80
     자
    0.80
    July
    0.79
    O
    0.79
    이
    0.78
    POSITIVE LOGITS
    ת
    0.93
    ر
    0.88
    ية
    0.84
    дцать
    0.82
    انى
    0.82
    انة
    0.82
    .
    0.78
    دين
    0.77
    انية
    0.77
    на
    0.76
    Activations Density 0.000%

    No Known Activations