© 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-16K
    7. 13619
    Prev
    Next
    INDEX
    Explanations

    harmless AI interactions

    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_16k_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
     insufficiently
    0.49
     it
    0.49
     insufficient
    0.48
     rather
    0.48
    而不是
    0.47
     outdated
    0.47
    В
    0.46
     wasn
    0.45
     недостаточно
    0.45
     It
    0.45
    POSITIVE LOGITS
     无
    0.52
     بے
    0.51
    txtarea
    0.47
    ಂಥ
    0.47
    purge
    0.47
    neutral
    0.46
    RAL
    0.46
     لام
    0.46
    yCoordinate
    0.46
     vô
    0.46
    Activations Density 0.475%

    No Known Activations