© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41674
    Prev
    Next
    INDEX
    Explanations

    distance away

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

    The neuron specializes in detecting numeric distance measurements in the text (e.g. float or integer values denoting miles or kilometers away).

    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
    }$
    -1.91
    狆
    -1.88
    这一次
    -1.76
    狲
    -1.72
     Nichts
    -1.68
     posled
    -1.66
    ”:
    -1.66
     …”
    -1.65
    lgari
    -1.60
    ];
    -1.55
    POSITIVE LOGITS
     they
    2.09
    j
    1.75
    髏
    1.72
    ientras
    1.70
     ``
    1.69
     estekak
    1.67
    .''
    1.66
    warran
    1.62
     что
    1.61
    A
    1.61
    Activations Density 0.006%

    No Known Activations