© 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. 34-GEMMASCOPE-RES-131K
    7. 32117
    Prev
    Next
    INDEX
    Explanations

    anticipate

    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_34/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
     québéco
    -0.81
    Qu
    -0.76
    两
    -0.74
     træ
    -0.73
    陰
    -0.73
     my
    -0.70
    Du
    -0.70
     Ответить
    -0.68
     és
    -0.68
    Sa
    -0.68
    POSITIVE LOGITS
     Donetsk
    1.12
     Kiev
    0.95
    chtes
    0.93
     bulat
    0.90
    rogenic
    0.90
     habet
    0.87
     ANTH
    0.87
    Ching
    0.86
     continuer
    0.85
    achite
    0.85
    Activations Density 0.007%

    No Known Activations