© 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. 48698
    Prev
    Next
    INDEX
    Explanations

    mention of

    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
     nhưng
    0.49
    原因
    0.44
    ٹرول
    0.44
    ী
    0.44
    ة
    0.43
    но
    0.42
    нию
    0.42
    하지만
    0.41
    បើ
    0.40
    зом
    0.40
    POSITIVE LOGITS
     cardiomyocytes
    0.45
     rigs
    0.43
     µ
    0.42
     cooperatives
    0.42
     efficacious
    0.42
     trajectories
    0.41
     jackets
    0.41
     commanders
    0.41
     gentle
    0.40
     treasures
    0.40
    Activations Density 0.001%

    No Known Activations