© 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. 4802
    Prev
    Next
    INDEX
    Explanations

    Mars exploration Curiosity rover

    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
    ัญ
    0.46
     seag
    0.41
     금액
    0.41
     중간
    0.39
     نجم
    0.39
    诮
    0.39
    谄
    0.39
    詎
    0.39
     reiterate
    0.38
    单纯
    0.38
    POSITIVE LOGITS
     crater
    0.75
     Martian
    0.69
     Mars
    0.68
     rover
    0.64
     methane
    0.63
     planetary
    0.61
     planet
    0.60
     Planetary
    0.59
     soil
    0.57
     craters
    0.57
    Activations Density 0.128%

    No Known Activations