© 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. 30799
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     狼
    -1.11
    回到了
    -1.06
     botellas
    -1.06
    dersfield
    -1.06
    了出来
    -1.05
     mereka
    -1.04
     obce
    -1.02
     there
    -1.02
     beauté
    -1.01
    pantalones
    -0.99
    POSITIVE LOGITS
    <blockquote>
    1.24
    /**
    1.24
    が
    1.01
    .\"
    0.99
    <h2>
    0.94
     
    0.93
    es
    0.92
    罫
    0.90
     dugaan
    0.90
    м
    0.90
    Activations Density 0.007%

    No Known Activations