© 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. 184
    Prev
    Next
    INDEX
    Explanations

    geography

    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
    木坂
    -2.20
    ];
    -2.13
    𖧵
    -2.11
    孭
    -2.00
    蓠
    -1.91
    怱
    -1.91
    颪
    -1.91
    のお知らせ
    -1.90
    𖣘
    -1.87
    齶
    -1.86
    POSITIVE LOGITS
    f
    2.44
    e
    2.27
    3
    2.23
    .
    2.20
    b
    2.09
    0
    2.00
    ve
    1.95
    </h4>
    1.89
    c
    1.83
     estekak
    1.80
    Activations Density 0.012%

    No Known Activations