© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56543
    Prev
    Next
    INDEX
    Explanations

    inch system, No blisters, between those

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

    "If you"

    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
    Negative Logits
    Betty
    0.64
    Candy
    0.55
    Irr
    0.52
    Colorful
    0.51
    灿
    0.51
    Multicolored
    0.50
    Palette
    0.50
    璀
    0.50
     रिस
    0.50
    itaj
    0.50
    POSITIVE LOGITS
     Mach
    0.45
     photographic
    0.45
    েকে
    0.40
    自行
    0.40
     mach
    0.39
    asto
    0.39
     asesor
    0.39
     aspek
    0.39
     ==
    0.39
     Michael
    0.39
    Activations Density 0.000%

    No Known Activations