© 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. 115681
    Prev
    Next
    INDEX
    Explanations

    party advisors

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

    containing

    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
    assembly
    0.56
    of
    0.55
    a
    0.53
     crystals
    0.46
     croc
    0.46
     postulates
    0.46
    reservoir
    0.46
     be
    0.46
    plates
    0.45
    activated
    0.45
    POSITIVE LOGITS
     Aly
    0.63
     सुम
    0.62
    
    0.60
     Aleg
    0.58
     Ciencias
    0.56
    ekkür
    0.55
     Quân
    0.55
     Thous
    0.54
    㤟
    0.54
     антен
    0.54
    Activations Density 0.001%

    No Known Activations