© 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. 68030
    Prev
    Next
    INDEX
    Explanations

    indispensable and submerged concepts

    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
    ка
    -2.94
    𓐍
    -2.92
     rafra
    -2.75
    𓍊
    -2.66
     menyen
    -2.58
    蕺
    -2.50
     visuel
    -2.48
     charmant
    -2.47
     berge
    -2.44
     faciliter
    -2.42
    POSITIVE LOGITS
    ).
    3.19
    ?
    3.05
    ↵↵
    2.91
    !
    2.91
    ’
    2.72
     and
    2.44
    s
    2.28
    d
    2.22
     \
    2.17
     in
    2.09
    Activations Density 0.003%

    No Known Activations