© 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. 145130
    Prev
    Next
    INDEX
    Explanations

    layer, priority, tending, complexity

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

    simplification, classification, increase, decline

    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
     eighty
    0.51
    '][$
    0.48
     Quaker
    0.47
     $,
    0.47
     yes
    0.46
     oui
    0.46
     Pictures
    0.45
     sixteen
    0.45
     Psal
    0.45
     oxen
    0.45
    POSITIVE LOGITS
    centro
    0.54
    and
    0.47
    targeted
    0.46
    V
    0.45
    aná
    0.45
    ind
    0.44
    onter
    0.44
    lán
    0.44
    administrat
    0.43
    J
    0.43
    Activations Density 0.000%

    No Known Activations