© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7084
    Prev
    Next
    INDEX
    Explanations

    un-words implying negativity or absence

    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
    -
    -2.61
     mitu
    -2.27
    槼
    -2.22
    >
    -2.20
     ухода
    -2.20
    戗
    -2.19
    }
    -2.19
    '
    -2.16
    you
    -2.14
    s
    -2.09
    POSITIVE LOGITS
    This
    2.41
    ه
    2.33
    ي
    2.23
    犽
    2.23
     entendi
    2.20
    owanym
    2.19
     prisonniers
    2.09
    исправ
    2.08
     gerekti
    2.02
    就跟
    2.00
    Activations Density 0.008%

    No Known Activations