© 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. 10-GEMMASCOPE-RES-131K
    7. 86123
    Prev
    Next
    INDEX
    Explanations

    the other day

    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_10/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
     When
    -1.55
     with
    -1.48
    ökk
    -1.35
     Nomor
    -1.34
     With
    -1.34
    XLS
    -1.31
     内衣
    -1.28
     magasiner
    -1.27
    通常
    -1.26
     géant
    -1.25
    POSITIVE LOGITS
     recently
    1.69
    quierda
    1.49
    ↵
    1.46
     недавно
    1.40
     lately
    1.39
    パパ
    1.30
     last
    1.30
     récemment
    1.30
     हाल
    1.28
    ᭄
    1.28
    Activations Density 0.020%

    No Known Activations