© 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. 34-GEMMASCOPE-RES-131K
    4. 70011
    Prev
    Next
    INDEX
    Explanations

    Attorney General, students, Speeches, Early experience, Recurrence

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

    The neuron is detecting long sequences of digits and numeric identifiers (e.g. docket or case numbers) in legal‐style headers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    step
    -0.83
     IC
    -0.76
     Hunting
    -0.69
    ake
    -0.68
     LCD
    -0.67
     ho
    -0.65
    *)
    -0.65
     IA
    -0.64
     IFN
    -0.63
    vible
    -0.63
    POSITIVE LOGITS
    CELLANEOUS
    0.89
     etab
    0.84
     venus
    0.84
     PERFORM
    0.83
     Zorg
    0.82
    ひら
    0.81
     magnifique
    0.81
    CITATION
    0.79
    ierungen
    0.79
     grail
    0.79
    Activations Density 0.010%

    No Known Activations