© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9747
    Prev
    Next
    INDEX
    Explanations

    classification or descriptor

    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
     and
    -1.47
    了过来
    -1.46
     our
    -1.45
     faulty
    -1.37
     ApiException
    -1.35
     four
    -1.32
     murieron
    -1.31
    salms
    -1.28
    four
    -1.27
    usitis
    -1.27
    POSITIVE LOGITS
    ॠ
    1.27
     that
    1.23
     banque
    1.22
     resim
    1.18
    素晴らしい
    1.13
     bulle
    1.13
     insec
    1.11
     chaine
    1.10
     Projet
    1.09
     ayah
    1.07
    Activations Density 0.656%

    No Known Activations