© 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. 106523
    Prev
    Next
    INDEX
    Explanations

    phone and tech product models

    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
     lenguas
    -1.09
     gegründet
    -1.03
     conductas
    -1.00
     creencias
    -1.00
    必要がある
    -0.98
    際には
    -0.96
    ようになる
    -0.95
     gezet
    -0.95
     zentralen
    -0.93
    <0x91>
    -0.92
    POSITIVE LOGITS
    看護
    0.90
     упаков
    0.90
     tillgäng
    0.88
     vertus
    0.88
     review
    0.84
    銘
    0.84
     obsidian
    0.83
    Zeneca
    0.82
    ργασ
    0.81
     смета
    0.81
    Activations Density 0.026%

    No Known Activations