© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113024
    Prev
    Next
    INDEX
    Explanations

    recalling past events

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

    The neuron detects cues of personal reminiscence and time-of-life reflection—words that signal talking about one’s own past experiences.

    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
     also
    -1.61
     according
    -1.52
    也
    -1.38
     has
    -1.26
    ">
    -1.26
    <sup>
    -1.19
     Everything
    -1.19
     também
    -1.17
     después
    -1.17
     based
    -1.16
    POSITIVE LOGITS
    borderSide
    1.25
     fön
    1.24
     rekla
    1.23
     Україні
    1.22
     Secrétaire
    1.21
    ೩
    1.21
     treff
    1.20
     Estaba
    1.20
     možná
    1.20
    </tfoot>
    1.19
    Activations Density 0.036%

    No Known Activations