© 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. 65430
    Prev
    Next
    INDEX
    Explanations

    ss sequence

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

    the abbreviation "ss" or "ssDNA" in technical and programming contexts.

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

    This neuron responds to occurrences of the letter sequence “ss” (double-s substrings).

    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
    ſelves
    -3.28
    骓
    -3.02
    迓
    -2.58
    芣
    -2.56
     весна
    -2.50
    鞮
    -2.48
    .
    -2.47
    鸸
    -2.41
    却被
    -2.39
     була
    -2.38
    POSITIVE LOGITS
    "
    3.45
    ss
    2.98
     begu
    2.42
    ?"
    2.41
     impec
    2.39
     You
    2.36
    et
    2.34
    *
    2.34
    !"
    2.34
    es
    2.30
    Activations Density 0.003%

    No Known Activations