© 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. 129895
    Prev
    Next
    INDEX
    Explanations

    poverty and its 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_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
    '
    -3.27
     –
    -2.55
    S
    -2.28
     Honestly
    -2.25
    不錯
    -2.22
    ?"
    -2.17
    过程中
    -2.17
    梘
    -2.16
     注文
    -2.13
    詎
    -2.13
    POSITIVE LOGITS
    .
    3.19
    遢
    2.63
     обеспечение
    2.59
    𖣔
    2.56
     nieuwe
    2.39
    鬟
    2.33
    </b>
    2.31
    呖
    2.25
     VERY
    2.22
     estos
    2.20
    Activations Density 0.004%

    No Known Activations