© 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. 196581
    Prev
    Next
    INDEX
    Explanations

    information to exercise

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

    organized pantry/storage space

    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
    PKG
    0.55
     unité
    0.54
    fiscal
    0.53
     quỹ
    0.50
    [,]
    0.48
    iš
    0.47
    are
    0.47
     fisk
    0.47
    matu
    0.46
    ιασ
    0.46
    POSITIVE LOGITS
     barium
    0.51
     plaster
    0.48
     cartoon
    0.46
     magnetic
    0.46
     magnesium
    0.45
     fluorine
    0.45
     $
    0.44
     fungal
    0.44
     radioactive
    0.44
     telegram
    0.44
    Activations Density 0.001%

    No Known Activations