© 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. 164760
    Prev
    Next
    INDEX
    Explanations

    satellite injection

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

    categories/types

    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
     substrates
    0.50
    ຕິດຕໍ່
    0.47
     crossovers
    0.47
    ἢ
    0.46
     lập
    0.45
    نگی
    0.45
     नमी
    0.45
     appliances
    0.45
     inhomogeneities
    0.44
     味
    0.44
    POSITIVE LOGITS
    书城
    0.47
     Chaucer
    0.45
     Baker
    0.44
    ዚያ
    0.43
     célé
    0.43
     Gor
    0.42
     Weber
    0.42
     begrü
    0.42
    巿
    0.42
     Krit
    0.42
    Activations Density 0.000%

    No Known Activations