© 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. 1017
    Prev
    Next
    INDEX
    Explanations

    ASC, ATF, lastName, OVA

    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
    )
    -3.00
    }
    -2.50
    -
    -2.44
     l
    -2.41
    曙
    -2.39
     en
    -2.33
    mē
    -2.30
    鲀
    -2.27
    も
    -2.25
    with
    -2.23
    POSITIVE LOGITS
    ⸱
    2.55
    螄
    2.52
    ”—
    2.52
    屙
    2.48
    鷽
    2.47
    いる
    2.45
     dovrà
    2.45
    厖
    2.42
    
    2.42
    犛
    2.38
    Activations Density 0.003%

    No Known Activations