© 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. 130330
    Prev
    Next
    INDEX
    Explanations

    objects being cleaned or repaired

    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
     geblieben
    -1.05
    ,
    -1.04
    IAT
    -0.92
    Bib
    -0.88
    リスク
    -0.88
    bibliography
    -0.86
    Recipe
    -0.85
     
    -0.84
     melissa
    -0.84
    BOM
    -0.84
    POSITIVE LOGITS
     repair
    1.12
    んでいた
    1.09
     manufacturers
    1.08
     damaged
    1.05
    rendre
    1.03
    Maak
    1.03
     marcato
    1.02
     cucchia
    1.02
    StatusEnum
    1.01
    borgen
    0.99
    Activations Density 0.053%

    No Known Activations