© 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. 34-GEMMASCOPE-RES-131K
    7. 83697
    Prev
    Next
    INDEX
    Explanations

    from a perspective analysis

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

    The neuron fires on numeric tokens (sequences of digits), i.e. it picks out numbers in the text.

    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
     pantaloni
    -0.95
    XmlSchema
    -0.94
    swire
    -0.91
    цуз
    -0.90
    apte
    -0.89
     jPanel
    -0.88
    lıkla
    -0.86
     scena
    -0.82
     Berman
    -0.82
    itse
    -0.81
    POSITIVE LOGITS
     perspective
    4.75
     standpoint
    4.75
    perspective
    3.20
     perspectives
    3.08
     viewpoint
    3.05
     Perspective
    2.92
    Perspective
    2.72
     perspectiva
    2.61
     PERSPECT
    2.27
     POV
    2.16
    Activations Density 0.044%

    No Known Activations