© 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. 42208
    Prev
    Next
    INDEX
    Explanations

    mang words

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

    The neuron detects occurrences of the character sequence “mang” in tokens.

    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
    }$
    -2.78
     verbess
    -2.67
    ’
    -2.44
     Tatsache
    -2.44
    是有
    -2.39
     Empfehlung
    -2.39
     Vielzahl
    -2.33
    揷
    -2.33
     erweiterten
    -2.31
    u
    -2.25
    POSITIVE LOGITS
    愎
    2.92
     segurando
    2.58
    <td>
    2.47
    C
    2.47
    H
    2.41
     豐
    2.27
     serán
    2.19
    O
    2.17
    Z
    2.16
    T
    2.14
    Activations Density 0.003%

    No Known Activations