© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129529
    Prev
    Next
    INDEX
    Explanations

    Halle lujah

    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
     as
    -1.30
     in
    -1.15
     how
    -1.14
     for
    -1.13
     getting
    -1.13
     does
    -1.12
     this
    -1.10
     one
    -1.09
     so
    -1.09
     How
    -1.03
    POSITIVE LOGITS
     meubles
    1.09
     NIST
    1.06
     matériaux
    1.02
     EIGHT
    1.02
     ACTIV
    1.01
    졍
    1.01
     terminer
    0.99
     eşofman
    0.98
     trám
    0.98
    Hj
    0.97
    Activations Density 0.001%

    No Known Activations