© 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. 123696
    Prev
    Next
    INDEX
    Explanations

    hedging and qualifying statements

    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
     striking
    0.45
     Inn
    0.45
     Lincoln
    0.43
     roug
    0.42
    у
    0.41
     Werk
    0.39
     Proceeds
    0.39
     well
    0.39
    িসি
    0.39
     Cari
    0.38
    POSITIVE LOGITS
     plasmids
    0.50
    ophobia
    0.46
    ()%
    0.46
    QRST
    0.46
     ਅਤੇ
    0.46
    Chef
    0.45
    緩
    0.45
    মতী
    0.45
    JLabel
    0.44
    opcode
    0.44
    Activations Density 0.004%

    No Known Activations