© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 38560
    Prev
    Next
    INDEX
    Explanations

    past participles and states

    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
     where
    -1.37
     from
    -1.27
     while
    -1.10
     during
    -1.08
     but
    -1.08
     for
    -1.08
     using
    -1.07
     on
    -1.06
     through
    -1.03
     लेकिन
    -1.03
    POSITIVE LOGITS
     themselves
    1.30
     refroid
    1.13
     katk
    1.05
     meren
    1.04
     makam
    1.04
    categorie
    1.02
    🪤
    1.02
     göm
    1.02
    upiter
    1.01
     elektrik
    1.01
    Activations Density 0.101%

    No Known Activations