© 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. 129553
    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
     any
    -1.42
     continued
    -1.34
     more
    -1.33
     which
    -1.29
    tidumbre
    -1.20
     who
    -1.13
    俳優
    -1.12
     ristorante
    -1.09
     other
    -1.07
     capas
    -1.07
    POSITIVE LOGITS
     recently
    2.72
    recently
    2.11
     recentemente
    2.03
     yesterday
    1.79
     недавно
    1.70
     previously
    1.68
     earlier
    1.65
     recientemente
    1.58
    Recently
    1.55
    為に
    1.43
    Activations Density 0.099%

    No Known Activations