© 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. 14696
    Prev
    Next
    INDEX
    Explanations

    past tense actions

    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
     hábiles
    -1.21
     detalladas
    -1.13
    ”
    -1.12
     позволяет
    -1.09
    S
    -1.07
     “
    -1.06
     säkert
    -1.06
    ことができる
    -1.05
     taken
    -1.05
     S
    -1.05
    POSITIVE LOGITS
     into
    1.41
     می‌شوند
    1.09
     katanya
    1.09
    —.
    1.08
     knop
    1.05
     dévelo
    1.05
    ± 
    1.05
    Diction
    1.05
     bicara
    1.02
    ܖ
    1.02
    Activations Density 0.055%

    No Known Activations