© 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. 1493
    Prev
    Next
    INDEX
    Explanations

    numbers and operators

    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
    ܀
    0.49
    menos
    0.46
    mär
    0.46
    shaped
    0.45
    ᄎ
    0.44
     तारीख
    0.44
    retr
    0.44
    s
    0.44
    astr
    0.43
    𝙍
    0.43
    POSITIVE LOGITS
     seven
    0.45
    θεί
    0.44
     permitted
    0.44
    ва
    0.41
     abandoned
    0.41
     buyout
    0.41
     directs
    0.40
    মুক্ত
    0.40
    独
    0.40
     mine
    0.40
    Activations Density 0.017%

    No Known Activations