© 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. 238127
    Prev
    Next
    INDEX
    Explanations

    dust and allergens

    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
    }}^
    0.52
     encant
    0.50
     위한
    0.49
     deadliest
    0.49
    tabPage
    0.48
     заяви
    0.48
     danza
    0.48
     פרו
    0.48
    ậc
    0.48
     싶은
    0.48
    POSITIVE LOGITS
    splitter
    0.43
    κα
    0.42
     skl
    0.42
    幾
    0.41
    صل
    0.41
    nect
    0.40
    GFR
    0.40
    reached
    0.40
    用地
    0.39
    elta
    0.39
    Activations Density 0.000%

    No Known Activations