© 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-65K
    7. 2725
    Prev
    Next
    INDEX
    Explanations

    hesitation and contemplation

    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_65k_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
    כ
    0.40
    และ
    0.40
     larges
    0.38
    )、
    0.38
    Codec
    0.38
     &
    0.38
     ਅਤੇ
    0.38
    、
    0.37
    )
    0.37
    和
    0.37
    POSITIVE LOGITS
     อืม
    0.59
     เอ่อ
    0.56
    哎
    0.54
    em
    0.50
     ehm
    0.49
    唉
    0.48
    surprisingly
    0.47
     ähm
    0.47
     Surprisingly
    0.46
    呃
    0.46
    Activations Density 0.070%

    No Known Activations