© 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. 111321
    Prev
    Next
    INDEX
    Explanations

    another recommendation

    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
     స్థ
    0.42
     помимо
    0.41
    諭
    0.41
    вати
    0.40
    ရှိ
    0.40
     शेअर
    0.40
    фектив
    0.40
    𝗱
    0.39
     เริ่ม
    0.39
     जरुरी
    0.39
    POSITIVE LOGITS
     another
    0.42
    或
    0.41
    另一
    0.40
     ANOTHER
    0.40
    Another
    0.40
    so
    0.39
     Testament
    0.39
     vagy
    0.39
    another
    0.39
    检查
    0.38
    Activations Density 0.005%

    No Known Activations