© 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. 10-GEMMASCOPE-RES-131K
    7. 111244
    Prev
    Next
    INDEX
    Explanations

    cob followed by English words

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

    The neuron consistently fires on occurrences of the character sequence “cob” (as part of words like cobweb, cobblestone, Cobas, Cobain, etc.).

    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
    ⩕
    -2.55
    A
    -2.45
     pelicula
    -2.39
    of
    -2.34
    鶿
    -2.33
    缡
    -2.30
    $
    -2.25
    髫
    -2.23
    鲼
    -2.14
    you
    -2.08
    POSITIVE LOGITS
    生意
    2.45
    媼
    2.36
    話が
    2.30
    老婆
    2.28
    釭
    2.27
     Если
    2.22
    瑒
    2.20
     vuestro
    2.19
     be
    2.16
    
    2.16
    Activations Density 0.003%

    No Known Activations