© 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. 14640
    Prev
    Next
    INDEX
    Explanations

    rev followed by version numbers or names

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

    The neuron activates on occurrences of the substring “rev,” i.e. tokens marking revisions or version identifiers.

    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
    ↵↵
    -3.19
    ]
    -2.69
     a
    -2.61
    ?
    -2.41
     speziellen
    -2.27
    越是
    -2.25
     vielfäl
    -2.22
     utilizan
    -2.17
     gleaming
    -2.16
    迨
    -2.16
    POSITIVE LOGITS
    屺
    2.55
    Ꮏ
    2.47
    想
    2.47
    ！"
    2.45
    獁
    2.42
    ///////
    2.41
    莢
    2.39
     gekocht
    2.39
    ༵
    2.36
     industrie
    2.33
    Activations Density 0.005%

    No Known Activations