© 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. 93555
    Prev
    Next
    INDEX
    Explanations

    html head section

    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
     Mauritania
    -0.83
    ḃ
    -0.81
     skai
    -0.79
    pork
    -0.76
     sabem
    -0.76
    锭
    -0.75
     Haig
    -0.73
     espe
    -0.72
    heits
    -0.71
    }$\\
    -0.71
    POSITIVE LOGITS
    title
    1.63
     title
    1.60
    meta
    1.33
     head
    1.22
    TITLE
    1.21
     meta
    1.13
     body
    1.12
    head
    1.09
    Title
    1.08
    style
    1.06
    Activations Density 0.042%

    No Known Activations