© 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. 84890
    Prev
    Next
    INDEX
    Explanations

    children, students, and supporting jobs

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

    describing how something sounds or is

    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
    求め
    0.48
    と思って
    0.46
    たら
    0.44
     masts
    0.44
    しも
    0.44
     mated
    0.43
     Australian
    0.42
     Antarctic
    0.42
     silos
    0.41
     corresponden
    0.41
    POSITIVE LOGITS
     vollständ
    0.49
     zwölf
    0.44
     neun
    0.42
     gennem
    0.42
     sieben
    0.42
    حض
    0.42
    ."],
    0.41
     gleichen
    0.41
     już
    0.41
     Absch
    0.41
    Activations Density 0.000%

    No Known Activations