© 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. 31972
    Prev
    Next
    INDEX
    Explanations

    tight and rope V

    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
     onSubmit
    0.40
     قريب
    0.39
    obaan
    0.38
    뼈
    0.38
    疊
    0.37
    Tommy
    0.37
    香
    0.37
     গোলে
    0.37
    ར་
    0.36
     বৃহৎ
    0.36
    POSITIVE LOGITS
     tight
    1.24
     Tight
    1.14
    Tight
    1.13
     tightness
    1.09
     tighter
    1.08
    tight
    1.03
     tightly
    0.91
     tighten
    0.88
    紧
    0.88
     tightening
    0.86
    Activations Density 0.004%

    No Known Activations