© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130698
    Prev
    Next
    INDEX
    Explanations

    northward, southward, eastward, westward

    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
     encantado
    -2.30
     vecin
    -2.22
     tomado
    -2.20
     mostrado
    -2.16
     cruzado
    -2.13
     cerrado
    -2.09
     personalizadas
    -2.08
     ヶ
    -2.08
     ausein
    -2.05
     escondido
    -2.05
    POSITIVE LOGITS
    )
    2.73
    ."
    2.64
    an
    2.59
    媄
    2.58
     "
    2.55
    of
    2.53
    ،
    2.47
    ，
    2.44
    actéristi
    2.44
    ',
    2.44
    Activations Density 0.007%

    No Known Activations