© 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. 84346
    Prev
    Next
    INDEX
    Explanations

    LaTeX environments

    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
     dando
    -1.62
    に関しては
    -1.45
    primarily
    -1.36
     ใช้
    -1.34
    も多く
    -1.31
     esche
    -1.29
     brill
    -1.28
     siè
    -1.28
     considerando
    -1.23
     indicando
    -1.23
    POSITIVE LOGITS
     with
    1.77
     what
    1.55
    Two
    1.54
    Before
    1.54
     Before
    1.53
    During
    1.51
    With
    1.49
     If
    1.48
    These
    1.45
     frightening
    1.41
    Activations Density 0.001%

    No Known Activations