© 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. 93293
    Prev
    Next
    INDEX
    Explanations

    independent voices

    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
     DG
    -0.80
    MV
    -0.80
     Ci
    -0.76
     egentligen
    -0.74
    DG
    -0.73
     Nit
    -0.73
     gut
    -0.73
     Mathematik
    -0.71
     cozy
    -0.71
    ii
    -0.71
    POSITIVE LOGITS
     Independent
    1.02
    ✕
    0.98
     INDEPENDENT
    0.93
     indy
    0.90
    Indy
    0.88
    independent
    0.87
     Proprietary
    0.85
     independent
    0.83
     tof
    0.83
    Worlds
    0.81
    Activations Density 0.009%

    No Known Activations