© 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. 71947
    Prev
    Next
    INDEX
    Explanations

    Jack Vallentyne, Occlusion, Many computer

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

    The neuron fires on standalone numbers (e.g. years, version numbers, numeric codes).

    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
     ſen
    -1.52
    糁
    -1.42
     investir
    -1.37
     corriger
    -1.35
     créer
    -1.35
    Mijn
    -1.34
    actéristi
    -1.32
    桫
    -1.30
    şil
    -1.30
     trám
    -1.30
    POSITIVE LOGITS
     and
    2.39
     one
    1.57
     what
    1.55
     has
    1.45
     four
    1.41
     seven
    1.39
     only
    1.38
     at
    1.36
     an
    1.35
     with
    1.34
    Activations Density 0.000%

    No Known Activations