© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91749
    Prev
    Next
    INDEX
    Explanations

    Discussion of related art

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

    The neuron is specialized to pick up stray standalone numbers—such as PDF page or margin line numbers—inserted by the document’s formatting rather than meaningful content.

    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
    ត
    -0.95
    ächtigen
    -0.94
     Boyce
    -0.94
    šanās
    -0.88
     even
    -0.82
     perquè
    -0.82
     '{@
    -0.82
     ava
    -0.81
     just
    -0.81
    Jar
    -0.81
    POSITIVE LOGITS
    似た
    0.92
    Chapitre
    0.86
    nady
    0.85
    毎回
    0.84
    IEnumerator
    0.84
     geprüft
    0.84
     bedankt
    0.83
    public
    0.82
    Transkript
    0.81
    leriyle
    0.81
    Activations Density 0.001%

    No Known Activations