© 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. 22-GEMMASCOPE-RES-131K
    7. 14060
    Prev
    Next
    INDEX
    Explanations

    names and schools

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

    The neuron responds strongly to named entities—proper names of people, organizations, schools, albums, etc.

    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
    を行い
    -1.48
    為に
    -1.43
     gestorben
    -1.34
    を行います
    -1.28
    さぁ
    -1.27
    ふと
    -1.24
    ほら
    -1.22
    感のある
    -1.19
    ごめん
    -1.17
    きち
    -1.16
    POSITIVE LOGITS
    האם
    1.20
    がありますが
    1.10
     когато
    1.06
    それも
    1.05
     with
    1.04
    眼鏡
    1.04
    これも
    1.02
    <0xA3>
    1.01
    などが
    0.99
    前は
    0.99
    Activations Density 0.042%

    No Known Activations