© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93059
    Prev
    Next
    INDEX
    Explanations

    math symbols and variables

    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
     impeccable
    -0.84
     or
    -0.84
     primarily
    -0.83
     Teufel
    -0.83
     nonché
    -0.82
     therefrom
    -0.81
     additional
    -0.81
    在家
    -0.80
    haji
    -0.79
     solely
    -0.79
    POSITIVE LOGITS
    」
    1.18
    』
    1.14
    stufen
    0.85
     baterie
    0.85
     citoyen
    0.84
     revenu
    0.82
     redé
    0.81
     spezi
    0.81
    ſs
    0.80
    ミニ
    0.80
    Activations Density 0.102%

    No Known Activations