© 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. 69259
    Prev
    Next
    INDEX
    Explanations

    with the distribution

    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
    埽
    -4.19
    秾
    -3.44
    𖣘
    -3.34
    ꜆
    -3.16
    
    -3.11
    蕷
    -2.95
    </i>
    -2.89
    eſ
    -2.83
    孭
    -2.80
    ⑉
    -2.78
    POSITIVE LOGITS
    </h4>
    3.36
     We
    3.20
    ⟞
    3.06
    趼
    2.98
    </em>
    2.97
    浥
    2.92
    摃
    2.89
     }
    2.83
    焄
    2.80
    </h2>
    2.75
    Activations Density 0.049%

    No Known Activations