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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109680
    Prev
    Next
    INDEX
    Explanations

    sound production and transmission

    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
    oggles
    -0.88
     کال
    -0.82
     teléfono
    -0.80
     APPELLANT
    -0.75
    esthes
    -0.74
     PLAINTIFF
    -0.73
     marché
    -0.72
    GRAFIA
    -0.72
     EDITORIAL
    -0.72
     GOODS
    -0.71
    POSITIVE LOGITS
     sound
    4.63
     sounds
    3.80
    sound
    3.38
    SOUND
    2.63
    Sound
    2.61
     Sound
    2.58
     зву
    2.58
     sonido
    2.53
     SOUND
    2.45
    sounds
    2.44
    Activations Density 0.059%

    No Known Activations