© 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. 199970
    Prev
    Next
    INDEX
    Explanations

    voice raspy, God, intention clearly

    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
    {
    0.45
    ონი
    0.44
     Usual
    0.41
    頭
    0.40
     ਡ
    0.40
    コム
    0.40
    -
    0.40
    ਾਲ
    0.39
    nH
    0.39
    ien
    0.39
    POSITIVE LOGITS
     cater
    0.50
     bởi
    0.50
     lá
    0.47
     belly
    0.46
    তত্ব
    0.44
     سبس
    0.44
     seasoning
    0.43
     পরিবর্তে
    0.43
     chuyển
    0.42
     bleach
    0.42
    Activations Density 0.008%

    No Known Activations