© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109062
    Prev
    Next
    INDEX
    Explanations

    bitwise complement or -1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adka
    -0.75
     hommes
    -0.75
     just
    -0.74
    료
    -0.71
     маль
    -0.71
    ₍
    -0.69
    รวม
    -0.69
    ción
    -0.67
    逸
    -0.67
     sinner
    -0.67
    POSITIVE LOGITS
    (~
    1.18
    MAX
    1.06
     billions
    1.02
     MAX
    0.98
    ~(
    0.97
     ~
    0.91
     maximal
    0.90
    ffffffff
    0.89
    ~
    0.88
    Max
    0.84
    Activations Density 0.031%

    No Known Activations