© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67991
    Prev
    Next
    INDEX
    Explanations

    since a past time

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

    The neuron detects temporal expressions and numeric time references (e.g. “since,” “before,” ages, dates, and other duration or time-point markers).

    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
    2
    -1.59
     with
    -1.42
    8
    -1.36
    9
    -1.30
    5
    -1.26
     electrónicos
    -1.21
    ↵↵
    -1.20
    囑
    -1.19
     båda
    -1.15
    有著
    -1.15
    POSITIVE LOGITS
     they
    1.78
     }],
    1.68
    );
    1.47
    __":
    1.45
    __':
    1.44
    itize
    1.38
    })}\
    1.38
    ))
    1.37
    ться
    1.36
    )
    1.36
    Activations Density 0.034%

    No Known Activations