© 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. 22-GEMMASCOPE-RES-131K
    4. 65792
    Prev
    Next
    INDEX
    Explanations

    geological periods and strata

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

    The neuron is keyed to geological references, especially names of time periods and rock formations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ૉ
    -1.48
    ſi
    -1.37
    これからの
    -1.35
     оружи
    -1.33
     nové
    -1.32
    jeros
    -1.29
     vlastnosti
    -1.27
    轳
    -1.27
     možnost
    -1.27
    шком
    -1.27
    POSITIVE LOGITS
     کرت
    1.27
    Mutagenicity
    1.24
     ancienne
    1.24
     earliest
    1.21
     saludables
    1.20
     фильтр
    1.18
     زیرا
    1.17
    Toluene
    1.16
     jeudi
    1.13
     són
    1.13
    Activations Density 0.016%

    No Known Activations