© 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. 22-GEMMASCOPE-RES-131K
    7. 39106
    Prev
    Next
    INDEX
    Explanations

    stage followed by level or context

    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_22/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
    俢
    -2.63
    鰱
    -2.39
    銲
    -2.30
    攆
    -2.27
    了起来
    -2.20
    齜
    -2.20
     rédig
    -2.16
     plunged
    -2.16
     publiek
    -2.13
    璈
    -2.13
    POSITIVE LOGITS
    y
    3.03
    }$.
    2.91
    ol
    2.63
    各样的
    2.61
    可以
    2.50
     renovations
    2.48
     необходимости
    2.48
    ar
    2.42
     berätt
    2.39
     необходимые
    2.39
    Activations Density 0.015%

    No Known Activations