© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31294
    Prev
    Next
    INDEX
    Explanations

    pickle or pickles

    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
     šk
    -0.73
     Seward
    -0.71
    الن
    -0.71
     тури
    -0.70
     Wagen
    -0.70
     iTunes
    -0.67
     Escrit
    -0.66
     Trotzdem
    -0.66
    pseudo
    -0.65
     Raid
    -0.65
    POSITIVE LOGITS
     pickle
    2.09
    Pickle
    1.80
     Pickle
    1.71
    pickle
    1.67
     pickles
    1.63
     Pickles
    1.54
     pickled
    1.50
    PICK
    1.25
    Pick
    1.25
     PICK
    1.23
    Activations Density 0.035%

    No Known Activations