© 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. 60522
    Prev
    Next
    INDEX
    Explanations

    excerpt from

    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
    {
    -1.68
    arching
    -1.48
     who
    -1.47
    }$
    -1.39
    ઁ
    -1.34
     desbloquear
    -1.34
    omato
    -1.31
    BeforeAll
    -1.30
    プーン
    -1.29
    
    -1.29
    POSITIVE LOGITS
     of
    1.90
    section
    1.59
     such
    1.55
     from
    1.55
    偁
    1.52
     "
    1.50
     Tonnen
    1.49
    䊏
    1.45
    lblNewLabel
    1.45
    ljeno
    1.41
    Activations Density 0.060%

    No Known Activations