© 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. 58200
    Prev
    Next
    INDEX
    Explanations

    transferred by, membership is, opportunities to

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

    connection to

    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
    w
    0.57
    room
    0.50
    h
    0.47
    那个
    0.45
    6
    0.45
     omdat
    0.44
    Architect
    0.43
    אות
    0.43
    archiv
    0.42
    4
    0.42
    POSITIVE LOGITS
     목적
    0.46
     sublattice
    0.45
     mexico
    0.44
     ಸು
    0.44
     snapping
    0.43
     permittivity
    0.43
     kahelaro
    0.42
     leptonic
    0.42
     напа
    0.42
     equatorial
    0.42
    Activations Density 0.000%

    No Known Activations