© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1328
    Prev
    Next
    INDEX
    Explanations

    inside locations and states

    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_10/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
    '
    -2.25
    </h3>
    -2.16
     I
    -1.90
    </em>
    -1.81
    1
    -1.74
    </h2>
    -1.73
    2
    -1.60
    </h4>
    -1.59
    <sup>
    -1.55
    一切都
    -1.48
    POSITIVE LOGITS
    ⾞
    1.85
    をしています
    1.77
    葙
    1.76
     persino
    1.70
    ꦮ
    1.64
    别人的
    1.63
    をしていた
    1.60
    斃
    1.59
    ᭝
    1.59
    が届
    1.56
    Activations Density 0.010%

    No Known Activations