© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102316
    Prev
    Next
    INDEX
    Explanations

    audible click or noise

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects occurrences of the substring “audible” (including forms like "inaudible") in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Accordingly
    -2.78
     While
    -2.41
     Хотя
    -2.38
     Interestingly
    -2.36
     During
    -2.34
     Therefore
    -2.30
     Presumably
    -2.25
     Undoubtedly
    -2.25
     Generally
    -2.25
    Most
    -2.25
    POSITIVE LOGITS
    ſſel
    3.06
    珵
    2.72
    锖
    2.70
     maakt
    2.69
    ㉕
    2.64
     использовании
    2.63
    廰
    2.59
    section
    2.50
     successes
    2.47
    }
    
    2.45
    Activations Density 0.005%

    No Known Activations