© 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. 123840
    Prev
    Next
    INDEX
    Explanations

    HTML link and line breaks

    np_acts-logits-general · gemini-2.5-flash-lite

    HTML line break tags `<br>` or `<br />`.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    了一個
    -1.43
    那種
    -1.42
    ついで
    -1.41
     була
    -1.39
     regarded
    -1.38
    違います
    -1.38
    𓇼
    -1.38
     podczas
    -1.36
     mildly
    -1.35
     Porém
    -1.35
    POSITIVE LOGITS
    3
    2.08
    2
    1.70
     особенно
    1.65
    部分
    1.64
    </sub>
    1.51
    9
    1.47
    NOK
    1.45
    ’，
    1.45
    inematic
    1.45
    ！”
    1.45
    Activations Density 0.003%

    No Known Activations