© 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. 10-GEMMASCOPE-RES-131K
    7. 74901
    Prev
    Next
    INDEX
    Explanations

    recovery and rebound

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

    The neuron fires strongly on words denoting recovery or revival (e.g. recovery, revive, recoverable, recovering).

    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
    MÁS
    -1.55
     regal
    -1.55
    Լ
    -1.52
     ответил
    -1.46
    FUENTES
    -1.45
    〰
    -1.41
    涠
    -1.40
    噫
    -1.40
    ⴷ
    -1.38
    urfacing
    -1.38
    POSITIVE LOGITS
     was
    1.77
     весна
    1.50
    じゃなくて
    1.48
     организма
    1.46
    就是
    1.43
    有
    1.43
     I
    1.38
    ."
    1.38
     ?
    1.37
    [
    1.37
    Activations Density 0.005%

    No Known Activations