© 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. 63125
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and five

    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
    starttime
    -0.74
     বল
    -0.73
    Netz
    -0.69
    七八
    -0.69
    צות
    -0.68
     Spinoza
    -0.68
    hsh
    -0.68
     Hepatitis
    -0.65
    histoire
    -0.64
     家族
    -0.64
    POSITIVE LOGITS
    5
    0.98
     '../
    0.93
     пя
    0.93
     fünf
    0.91
     ۵
    0.91
     fifth
    0.89
     Fifth
    0.89
    ৫
    0.89
     five
    0.88
    five
    0.85
    Activations Density 0.039%

    No Known Activations