© 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. 30967
    Prev
    Next
    INDEX
    Explanations

    python pickle and license information

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on embedded Python “pickle” serialization markers (e.g. `<pickle>` tags and associated numeric data).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Cabbage
    -0.79
     DEATH
    -0.75
     sama
    -0.72
     cober
    -0.72
     LAWS
    -0.71
    Lavender
    -0.71
    Groeten
    -0.71
     Tér
    -0.71
    ebles
    -0.71
    homes
    -0.71
    POSITIVE LOGITS
     pamię
    0.80
     earphone
    0.74
     weep
    0.72
     testis
    0.72
     BSEB
    0.69
     handout
    0.68
     过
    0.68
     jungles
    0.67
    (!_
    0.67
    Nelson
    0.67
    Activations Density 0.052%

    No Known Activations