© 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. 208539
    Prev
    Next
    INDEX
    Explanations

    mentioning tribute, lot, talked, brand

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

    marketplace of ideas

    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
    𝓖
    0.50
    ništva
    0.49
    پ
    0.46
    Geschichte
    0.45
    ９
    0.44
    𝓙
    0.44
    ಣಿ
    0.44
    ℡
    0.44
    Overall
    0.43
     persönlich
    0.43
    POSITIVE LOGITS
     Pigs
    0.48
     commence
    0.46
     kud
    0.45
     and
    0.44
     we
    0.44
     véd
    0.43
     már
    0.43
    rukt
    0.43
    lick
    0.43
     brand
    0.42
    Activations Density 0.001%

    No Known Activations