© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71546
    Prev
    Next
    INDEX
    Explanations

    story arcs and plotlines

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

    The neuron activates on mentions of narrative “arc” or “storyline” (often with numbers), i.e. references to story arcs.

    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
    }
    -2.58
    t
    -2.41
     Despite
    -2.25
     It
    -2.20
     themſelves
    -2.17
     Although
    -2.13
     $^{
    -2.06
     Unlike
    -2.06
    bernador
    -2.06
    </td>
    -2.03
    POSITIVE LOGITS
    '
    2.86
    
    2.64
    ſu
    2.30
    僰
    2.20
    迨
    2.20
    啵
    2.16
    嚶
    2.14
     lament
    2.09
     he
    2.09
     integrante
    2.08
    Activations Density 0.004%

    No Known Activations