© 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. 102380
    Prev
    Next
    INDEX
    Explanations

    sounds and audio

    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
     decal
    -0.79
     тан
    -0.78
     cameras
    -0.77
     ophthal
    -0.76
     riffs
    -0.76
     ransomware
    -0.75
    zzles
    -0.74
     dancing
    -0.73
     ink
    -0.73
     Ophthal
    -0.73
    POSITIVE LOGITS
     sounds
    2.17
     sound
    2.02
     зву
    1.58
     ambience
    1.52
    sounds
    1.50
     Sounds
    1.47
     ambient
    1.47
     noises
    1.41
     Sound
    1.39
    Sounds
    1.39
    Activations Density 0.024%

    No Known Activations