© 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. 22-GEMMASCOPE-RES-131K
    4. 54409
    Prev
    Next
    INDEX
    Explanations

    intent extra, distance modulus, packaged for

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

    The neuron flags tokens that serve as technical qualifiers or “units” immediately following numbers—e.g. time units, version or measurement labels, statistical or domain‐specific descriptors that come right after numeric values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     gemaakt
    -1.09
     آمریکایی
    -1.09
    átor
    -0.99
    
    -0.98
     hır
    -0.98
     berdasarkan
    -0.98
     защото
    -0.97
     ankaŭ
    -0.97
    hounds
    -0.96
    を行いました
    -0.96
    POSITIVE LOGITS
    Anexo
    0.93
    endphp
    0.92
    Troubleshooting
    0.91
    Causas
    0.88
    ться
    0.87
    }},
    0.86
    𝚞
    0.86
    帥
    0.84
    should
    0.84
     But
    0.84
    Activations Density 0.101%

    No Known Activations