© 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. 77154
    Prev
    Next
    INDEX
    Explanations

    xml prefixes and attributes

    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
     twelve
    -1.19
     Twelve
    -1.16
    Twelve
    -1.14
    ۱۲
    -0.91
    ýl
    -0.85
    twelve
    -0.84
    十二
    -0.82
     zwölf
    -0.81
     Duane
    -0.81
     ۱۲
    -0.77
    POSITIVE LOGITS
     xvii
    0.77
    ffffff
    0.68
    freight
    0.67
    pagni
    0.67
    witter
    0.66
     Ich
    0.66
    עי
    0.65
     CHICKEN
    0.65
    }-{
    0.65
     CONTRACT
    0.65
    Activations Density 0.708%

    No Known Activations