© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54401
    Prev
    Next
    INDEX
    Explanations

    explaining ancient life and evolution

    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_40_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
    龙头
    0.52
    龙
    0.49
    Jurassic
    0.42
    龍
    0.42
     सैकड़ों
    0.42
     ജൂ
    0.41
    䪲
    0.40
    (`#
    0.40
     ब्लू
    0.39
    पेश
    0.38
    POSITIVE LOGITS
     Miocene
    0.55
     mammalian
    0.48
     Tertiary
    0.47
     mammal
    0.47
     Olig
    0.44
     mammals
    0.43
     tertiary
    0.43
     rodent
    0.43
     gambling
    0.41
     primate
    0.40
    Activations Density 0.027%

    No Known Activations