© 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. 119087
    Prev
    Next
    INDEX
    Explanations

    speech endpoint detection

    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
     daybreak
    -0.74
     frets
    -0.73
     JIT
    -0.72
     Braille
    -0.71
    NullCheck
    -0.71
    فاع
    -0.70
    연
    -0.69
     erreicht
    -0.68
     obel
    -0.68
     palp
    -0.68
    POSITIVE LOGITS
     speech
    1.15
     beam
    0.98
    speech
    0.88
     Speech
    0.88
     Beam
    0.84
    intelligible
    0.84
    AEC
    0.84
    ={}
    0.84
     Приступљено
    0.84
    лея
    0.83
    Activations Density 0.032%

    No Known Activations