© 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. 22-GEMMASCOPE-RES-131K
    7. 128087
    Prev
    Next
    INDEX
    Explanations

    broadcasting channels and stations

    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_22/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
     también
    -1.60
     também
    -1.45
     cualquier
    -1.38
     также
    -1.31
     múltiples
    -1.28
     involving
    -1.23
     również
    -1.23
    ]=\
    -1.23
     letzten
    -1.20
     probablemente
    -1.20
    POSITIVE LOGITS
    uyasha
    1.42
     broadcasting
    1.34
     broadcast
    1.33
    ерез
    1.33
     gorro
    1.30
     frequencies
    1.23
     боли
    1.20
     channels
    1.19
     INTERVIEW
    1.18
     stric
    1.17
    Activations Density 0.090%

    No Known Activations