© 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. 8160
    Prev
    Next
    INDEX
    Explanations

    import or .h

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

    The neuron is triggered by CamelCase or PascalCase identifiers (multi‐word names starting with uppercase letters).

    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
     prevé
    -1.71
    ⎆
    -1.57
     unfailing
    -1.57
    ⮑
    -1.55
     conoció
    -1.44
    :……
    -1.44
     staffel
    -1.41
     ſont
    -1.41
     mauva
    -1.41
    めで
    -1.38
    POSITIVE LOGITS
     or
    1.96
     this
    1.65
    .
    1.61
    or
    1.47
     while
    1.42
     as
    1.41
    else
    1.40
    <
    1.37
     one
    1.36
    }
    1.36
    Activations Density 0.027%

    No Known Activations