© 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. 31585
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
    ZZA
    -0.84
    зре
    -0.82
     减
    -0.81
    risi
    -0.78
     IMHO
    -0.77
    olusi
    -0.76
    tigas
    -0.76
     estilo
    -0.75
     hygge
    -0.75
    EDOM
    -0.75
    POSITIVE LOGITS
    )',
    0.86
     sprawia
    0.83
    tokine
    0.81
     adquisición
    0.79
    minecraft
    0.77
    </em>
    0.75
     <=",
    0.74
    down
    0.73
    Saj
    0.72
    Díky
    0.72
    Activations Density 0.002%

    No Known Activations