© 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. 99884
    Prev
    Next
    INDEX
    Explanations

    young people and students

    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
    Pued
    -0.78
    mouthed
    -0.78
    ograms
    -0.77
    iempos
    -0.77
    الیا
    -0.76
    nnn
    -0.76
    sitions
    -0.76
    getVersion
    -0.76
    Leaders
    -0.74
     agresión
    -0.74
    POSITIVE LOGITS
     multipliers
    1.06
     przecież
    0.92
     심
    0.90
     merry
    0.89
    inizi
    0.84
     Reihenfolge
    0.84
     Selby
    0.82
     motorized
    0.81
     aparentemente
    0.81
     sév
    0.81
    Activations Density 0.030%

    No Known Activations