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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69766
    Prev
    Next
    INDEX
    Explanations

    field work and research contexts

    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
     strangle
    -2.42
    ↵
    -2.41
    卺
    -2.22
    を重ね
    -2.22
    甭
    -2.20
    餿
    -2.19
    ﾏ
    -2.16
    岨
    -2.13
     disdain
    -2.06
    齎
    -2.06
    POSITIVE LOGITS
     But
    2.98
     namun
    2.55
    ]
    2.45
    炝
    2.36
    、“
    2.34
     pero
    2.31
     mutta
    2.30
     แต่
    2.28
    で
    2.28
    </strong>
    2.27
    Activations Density 0.042%

    No Known Activations