© 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. 10-GEMMASCOPE-RES-131K
    7. 105855
    Prev
    Next
    INDEX
    Explanations

    Spielberg, Blum, KeyDown, DateTimeField

    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
    
    -2.81
    辚
    -2.47
    鶿
    -2.42
    鰾
    -2.38
     explot
    -2.38
    大概是
    -2.28
    莛
    -2.23
     pese
    -2.22
    ن
    -2.20
     {
    -2.19
    POSITIVE LOGITS
    𔘓
    3.00
    嵛
    2.73
    }{
    2.63
    }$
    2.59
     رائع
    2.53
    ci
    2.36
     $^{\
    2.30
    t
    2.28
     ребёнка
    2.27
    with
    2.22
    Activations Density 0.021%

    No Known Activations