© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57212
    Prev
    Next
    INDEX
    Explanations

    $this

    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
    ıyoruz
    -0.92
    роки
    -0.91
     voient
    -0.89
    🏒
    -0.89
    猖
    -0.85
    aupun
    -0.85
     emotions
    -0.85
     traité
    -0.84
     ویت
    -0.84
    ()][
    -0.83
    POSITIVE LOGITS
     this
    5.00
    this
    2.55
     This
    1.98
     этом
    1.97
     этого
    1.88
     này
    1.88
     этой
    1.84
    นี้
    1.77
     هذا
    1.76
     these
    1.67
    Activations Density 0.006%

    No Known Activations