© 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. 13755
    Prev
    Next
    INDEX
    Explanations

    He or she followed by an action/state

    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
    風景
    -1.19
     einzelne
    -1.05
     Ebenen
    -1.04
    一样的
    -1.04
     \&
    -1.02
    o
    -1.01
    態度
    -1.00
    中には
    -0.99
    因为它
    -0.96
     O
    -0.95
    POSITIVE LOGITS
    corrhi
    1.41
     necesitar
    1.34
    の方に
    1.25
    泐
    1.19
    際に
    1.14
     parecía
    1.13
     škoda
    1.13
     contaba
    1.13
     NÃO
    1.12
    seag
    1.12
    Activations Density 0.046%

    No Known Activations