© 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. 55851
    Prev
    Next
    INDEX
    Explanations

    microphone and camcorder audio recording

    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
     radic
    -0.80
     drafted
    -0.79
     commissioned
    -0.79
     cytometry
    -0.77
     Ramírez
    -0.77
     dynamical
    -0.77
     cry
    -0.75
    KN
    -0.74
    iken
    -0.71
     επι
    -0.70
    POSITIVE LOGITS
     recorder
    0.81
     Deity
    0.80
    recorder
    0.76
     recorders
    0.76
     Interview
    0.76
    recording
    0.76
     Rode
    0.75
    ennheiser
    0.70
    lelő
    0.68
     investigador
    0.67
    Activations Density 0.019%

    No Known Activations