© 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. 13995
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions

    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
    严重
    0.44
     jelas
    0.42
    明显
    0.40
    艿
    0.40
    减少
    0.39
    ಾದರೆ
    0.39
     দিক
    0.38
    会让
    0.38
    移
    0.38
    认为是
    0.38
    POSITIVE LOGITS
    のだが
    0.49
     veterinary
    0.47
     veterin
    0.46
     gour
    0.44
     אך
    0.43
     la
    0.43
    បុ
    0.42
     tunable
    0.42
     maar
    0.42
     ancak
    0.42
    Activations Density 0.010%

    No Known Activations