© 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. 28557
    Prev
    Next
    INDEX
    Explanations

    greeting and meeting others

    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
     improves
    0.50
     其
    0.42
    καν
    0.42
     Improves
    0.41
     its
    0.40
     quantities
    0.40
     acceptable
    0.38
     testicule
    0.38
     fulfills
    0.38
    其
    0.38
    POSITIVE LOGITS
     знать
    0.68
    Having
    0.61
     having
    0.60
     biết
    0.58
     thấy
    0.58
     seeing
    0.56
     увидеть
    0.56
    avoir
    0.55
    having
    0.54
     mieć
    0.54
    Activations Density 0.039%

    No Known Activations