© 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. 243933
    Prev
    Next
    INDEX
    Explanations

    permanent establishment

    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
    优势
    0.51
    ৰ
    0.48
    囪
    0.48
    Algun
    0.47
     comunicarse
    0.46
    Recorded
    0.45
    ता
    0.45
     efectuar
    0.45
     yattha
    0.45
    ṟ
    0.44
    POSITIVE LOGITS
     (
    0.51
     gasket
    0.47
    rikes
    0.47
    enties
    0.47
     Führ
    0.46
    lite
    0.46
     d
    0.45
    cooler
    0.45
     sk
    0.45
    s
    0.45
    Activations Density 0.002%

    No Known Activations