© 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. 108901
    Prev
    Next
    INDEX
    Explanations

    mathematical or code symbols

    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
     specialmente
    -1.02
     volete
    -0.83
     policiais
    -0.82
    uação
    -0.81
     persino
    -0.79
    olites
    -0.77
    ując
    -0.75
     erscheint
    -0.75
     haji
    -0.75
     vermag
    -0.75
    POSITIVE LOGITS
     iki
    0.96
     zwei
    0.93
     olacaktır
    0.92
     dön
    0.92
     sesuatu
    0.90
     educativas
    0.89
    ニッシュ
    0.88
    förmig
    0.88
    нской
    0.85
    (;;)
    0.85
    Activations Density 0.036%

    No Known Activations