© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 10855
    Prev
    Next
    INDEX
    Explanations

    login success or failure

    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_22/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
    0
    -3.75
    </h4>
    -2.86
     .
    -2.55
    {
    -2.41
    t
    -2.41
    v
    -2.38
    訁
    -2.28
     —
    -2.25
    and
    -2.25
     It
    -2.20
    POSITIVE LOGITS
     felpa
    2.70
     帅气
    2.67
    鬈
    2.53
    合适的
    2.52
    栊
    2.39
     tonel
    2.34
    ᠁
    2.34
     doctors
    2.34
     garganta
    2.33
    ?):
    2.33
    Activations Density 0.008%

    No Known Activations