© 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. 13906
    Prev
    Next
    INDEX
    Explanations

    avocados, oil, Ramadan, LinkedIn, CDN

    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
    т
    0.53
    ל
    0.53
    โ
    0.52
     של
    0.52
     הא
    0.50
     רק
    0.50
    ш
    0.49
    ห
    0.49
    ส
    0.48
     ਇਸ
    0.47
    POSITIVE LOGITS
     Citrus
    0.44
     Position
    0.41
     allocates
    0.41
     Development
    0.40
     streamlines
    0.39
     organi
    0.39
     ruchu
    0.38
     Tomatoes
    0.38
     Procurement
    0.38
     habilidades
    0.38
    Activations Density 0.133%

    No Known Activations