© 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. 63151
    Prev
    Next
    INDEX
    Explanations

    students, youth, children, citizens, consumers

    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
     Hote
    -0.78
    малар
    -0.76
     הָ
    -0.75
     dejen
    -0.74
     pooled
    -0.73
    盛り
    -0.71
     faç
    -0.71
     transpired
    -0.70
    至今
    -0.69
     senz
    -0.69
    POSITIVE LOGITS
    operability
    0.91
    dimento
    0.88
     επ
    0.84
     skipper
    0.84
    ਓ
    0.82
     charter
    0.82
     Walden
    0.81
     Cent
    0.81
     Charter
    0.81
     Governor
    0.80
    Activations Density 0.030%

    No Known Activations