© 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. 22-GEMMASCOPE-RES-131K
    7. 98228
    Prev
    Next
    INDEX
    Explanations

    person followed by description

    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
    corrhi
    -1.83
    cobacterium
    -1.51
    明日は
    -1.45
    ślę
    -1.45
    になるので
    -1.45
    carus
    -1.43
     роско
    -1.42
     their
    -1.41
    说起
    -1.39
     ихъ
    -1.39
    POSITIVE LOGITS
     is
    3.16
     are
    2.31
     was
    2.16
    は
    1.97
     has
    1.92
     have
    1.53
    が
    1.52
     (
    1.48
    явля
    1.41
     had
    1.40
    Activations Density 0.160%

    No Known Activations