© 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. 20894
    Prev
    Next
    INDEX
    Explanations

    reminder of something

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

    The neuron strongly activates on occurrences of the word “reminder” (in any context or casing).

    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
    '
    -3.28
    2
    -3.08
    s
    -2.91
     we
    -2.81
    ]
    -2.63
     avec
    -2.61
    -
    -2.61
    4
    -2.56
    }$
    -2.56
    y
    -2.53
    POSITIVE LOGITS
    趼
    2.84
     camiset
    2.55
    鰾
    2.50
    酹
    2.48
    谞
    2.47
     extrêmement
    2.44
    灕
    2.41
    焿
    2.39
    縯
    2.39
    𖡼
    2.36
    Activations Density 0.002%

    No Known Activations