© 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. 34-GEMMASCOPE-RES-131K
    7. 91498
    Prev
    Next
    INDEX
    Explanations

    being held or imprisoned

    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
    digde
    -0.82
    ýchod
    -0.79
    ảnh
    -0.73
    jątk
    -0.72
     界
    -0.71
    Destroyed
    -0.69
     gelangen
    -0.67
     foldable
    -0.67
     mukaan
    -0.66
     чек
    -0.65
    POSITIVE LOGITS
     confinement
    2.84
     incarceration
    2.70
     imprisoned
    2.70
     imprisonment
    2.67
     incarcerated
    2.45
     imprison
    2.39
     detained
    2.36
     housed
    2.33
     confined
    2.17
     incarcer
    2.16
    Activations Density 0.074%

    No Known Activations