© 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. 11025
    Prev
    Next
    INDEX
    Explanations

    certainty adverbs after comma

    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
     privind
    0.49
     policías
    0.44
     gloves
    0.44
     กับ
    0.44
     protože
    0.43
     perchè
    0.42
    攞
    0.42
    ൊന്നും
    0.42
    ريبة
    0.42
    ಿರುವ
    0.41
    POSITIVE LOGITS
    ,
    0.59
     ,
    0.55
     oczywiście
    0.50
     ultimately
    0.47
     undoubtedly
    0.46
     O
    0.45
     itself
    0.45
     undoubt
    0.44
     appunto
    0.44
     unequivocally
    0.44
    Activations Density 0.032%

    No Known Activations