© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184780
    Prev
    Next
    INDEX
    Explanations

    massive galaxies

    np_acts-logits-general · gemini-2.5-flash-lite

    hypothetical questions or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    生涯
    0.40
    構
    0.40
    邾
    0.39
    alura
    0.39
    埸
    0.38
     попыта
    0.38
    豢
    0.38
    ∩
    0.38
     결정
    0.37
    律
    0.37
    POSITIVE LOGITS
     recovery
    0.48
     breakthroughs
    0.46
     yields
    0.46
     kırmızı
    0.45
     soils
    0.44
     nutrient
    0.44
     dugo
    0.44
     nimble
    0.44
     lubricants
    0.43
     zippers
    0.43
    Activations Density 0.002%

    No Known Activations