© 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. 92669
    Prev
    Next
    INDEX
    Explanations

    XML structure, configuration

    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
     when
    -1.10
    ﷽
    -1.01
    Suka
    -1.00
    iją
    -0.98
    ilaian
    -0.96
     new
    -0.95
     ostensibly
    -0.94
     Nearly
    -0.92
    könig
    -0.92
     belki
    -0.91
    POSITIVE LOGITS
    </strong>
    1.01
    是一
    0.96
     ۰
    0.95
     áng
    0.93
     моменты
    0.92
    inWeight
    0.91
    де
    0.90
    ]
    0.90
     ваше
    0.88
    iedene
    0.88
    Activations Density 0.002%

    No Known Activations