© 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. 11552
    Prev
    Next
    INDEX
    Explanations

    mutants

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

    X-Men and mutant-related content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects comic‐book issue identifiers, particularly “X-” titles (e.g. X-Men, Giant-Size X-Men) and their issue numbers.

    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
     новых
    -2.00
    祧
    -1.66
    ulsión
    -1.59
     perú
    -1.55
     большая
    -1.54
     그는
    -1.53
    出發
    -1.53
    鴴
    -1.51
    美味しかった
    -1.51
    美味しそう
    -1.50
    POSITIVE LOGITS
     mehreren
    1.60
    isation
    1.56
    ’,
    1.55
    然后
    1.48
     dört
    1.48
     REAL
    1.44
     THEN
    1.41
    <td>
    1.38
    okko
    1.37
    f
    1.36
    Activations Density 0.007%

    No Known Activations