© 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. 117418
    Prev
    Next
    INDEX
    Explanations

    `\cr` or LaTeX `\alias`

    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
    tedy
    -0.93
    UKO
    -0.86
    <h3>
    -0.85
     Campe
    -0.84
     garant
    -0.78
    »،
    -0.78
    Hern
    -0.77
    FRED
    -0.75
     adorno
    -0.75
    נטר
    -0.74
    POSITIVE LOGITS
    ]-->
    0.80
    デーション
    0.80
    yses
    0.76
     трен
    0.75
     into
    0.75
     achieving
    0.74
    sync
    0.74
    父の
    0.73
    連合
    0.73
     Sync
    0.73
    Activations Density 0.008%

    No Known Activations