© 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. 3842
    Prev
    Next
    INDEX
    Explanations

    identifying concepts and their properties

    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
    rakt
    0.30
    蹂
    0.28
    റ്റ്
    0.27
     ذریع
    0.27
     ٹوٹ
    0.27
     செய்தி
    0.26
    晠
    0.26
     相关
    0.26
    ០
    0.26
     ಮಾಹಿತಿ
    0.26
    POSITIVE LOGITS
     is
    0.56
     has
    0.52
     does
    0.48
     have
    0.47
     consists
    0.43
     had
    0.42
     είναι
    0.42
     provides
    0.42
     are
    0.41
     was
    0.41
    Activations Density 0.232%

    No Known Activations