© 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. 53-GEMMASCOPE-2-RES-262K
    7. 165862
    Prev
    Next
    INDEX
    Explanations

    topic marker

    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_53_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
    耂
    0.42
     KRS
    0.40
    ẽ
    0.40
     बुनिया
    0.40
    てる
    0.39
    耇
    0.39
    quele
    0.38
    ҹ
    0.38
     croire
    0.38
     Cak
    0.37
    POSITIVE LOGITS
     departure
    0.41
    损害
    0.41
    reece
    0.38
    resent
    0.38
     শরীর
    0.37
    Departure
    0.37
    replay
    0.36
    带
    0.36
    Britain
    0.35
     karakteristik
    0.35
    Activations Density 0.003%

    No Known Activations