© 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. 129743
    Prev
    Next
    INDEX
    Explanations

    starts with unre

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

    The neuron fires on occurrences of the character sequence “unre,” i.e. words beginning with the “unre-” prefix.

    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
    lgari
    -2.86
     și
    -2.64
     और
    -2.53
    >
    -2.50
    żli
    -2.45
     và
    -2.34
    \},
    -2.20
    และ
    -2.19
     και
    -2.16
    QMetaType
    -2.14
    POSITIVE LOGITS
    d
    3.42
    縢
    2.70
    n
    2.58
    2
    2.56
    k
    2.39
    c
    2.34
    }
    2.30
    ጴ
    2.28
    7
    2.27
    l
    2.22
    Activations Density 0.003%

    No Known Activations