© 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. 66097
    Prev
    Next
    INDEX
    Explanations

    hindering access, movement, progress, or communication

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

    The neuron fires on occurrences of the verb “hinder” (and its inflected forms) indicating obstruction or prevention.

    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
    ﹅
    -2.97
     борьбе
    -2.81
    猻
    -2.44
    铤
    -2.36
     patrie
    -2.34
    栳
    -2.33
     saluti
    -2.30
    ⸒
    -2.30
     icône
    -2.28
    瓩
    -2.28
    POSITIVE LOGITS
    );
    2.53
    ),
    2.48
     habrían
    2.44
     $
    2.38
     beberapa
    2.34
    蹕
    2.33
    一方面
    2.30
     and
    2.30
     Their
    2.27
     murieron
    2.22
    Activations Density 0.002%

    No Known Activations