© 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. 58246
    Prev
    Next
    INDEX
    Explanations

    aftercare and aftermarket services

    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
    らしく
    -0.91
    racht
    -0.90
    させ
    -0.77
    ården
    -0.74
    спасибо
    -0.74
    madol
    -0.74
    uel
    -0.72
    小结
    -0.71
    ثمار
    -0.70
    newnode
    -0.69
    POSITIVE LOGITS
     after
    3.89
    after
    3.00
     после
    2.89
    After
    2.89
    AFTER
    2.80
    售后
    2.77
     After
    2.77
     après
    2.72
     AFTER
    2.72
     після
    2.56
    Activations Density 0.023%

    No Known Activations