© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60877
    Prev
    Next
    INDEX
    Explanations

    voice and telephone services

    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
     zufolge
    -0.75
     variational
    -0.75
    esch
    -0.72
     посу
    -0.71
    zynski
    -0.68
    őd
    -0.68
    リモ
    -0.68
     podle
    -0.67
     сете
    -0.66
    licates
    -0.66
    POSITIVE LOGITS
     voice
    4.22
    voice
    3.23
    Voice
    2.98
     Voice
    2.91
     voix
    2.55
     VOICE
    2.44
     voices
    2.34
    VOICE
    2.31
     voz
    2.06
     голос
    1.98
    Activations Density 0.089%

    No Known Activations