© 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. 22-GEMMASCOPE-RES-131K
    7. 15458
    Prev
    Next
    INDEX
    Explanations

    loving milk or similar 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_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
     overall
    -1.44
     tersebut
    -1.37
    Approximately
    -1.27
    subaru
    -1.23
    がんば
    -1.23
     development
    -1.23
     پژ
    -1.23
     மற்றும்
    -1.23
     resulting
    -1.22
    cienza
    -1.21
    POSITIVE LOGITS
     včetně
    1.52
     any
    1.49
    licopter
    1.46
    editary
    1.41
     anybody
    1.38
     azeite
    1.32
     no
    1.31
     Daß
    1.30
    🪛
    1.29
     yöntem
    1.28
    Activations Density 0.003%

    No Known Activations