© 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. 34-GEMMASCOPE-RES-131K
    7. 75621
    Prev
    Next
    INDEX
    Explanations

    past perfect had

    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
    физи
    -0.82
    ']))
    -0.82
    ėtų
    -0.79
    ktm
    -0.79
     хотела
    -0.76
    cstr
    -0.76
     anderson
    -0.75
     possam
    -0.75
    gewicht
    -0.74
     számára
    -0.73
    POSITIVE LOGITS
     had
    7.13
    Had
    4.06
     Had
    3.33
     hatte
    3.27
    had
    3.25
     hatten
    3.14
     avuto
    3.03
     tenido
    3.03
     είχε
    2.92
     tuvo
    2.67
    Activations Density 0.181%

    No Known Activations