© 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. 73899
    Prev
    Next
    INDEX
    Explanations

    72 and other numbers

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

    The neuron is tuned to detect numeric tokens (multi‐digit numbers).

    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
     Besonder
    -3.03
    訁
    -2.92
     meget
    -2.69
     a
    -2.64
     Entste
    -2.63
     ۶
    -2.48
     anderes
    -2.33
    趿
    -2.31
     incrível
    -2.30
     emocionante
    -2.30
    POSITIVE LOGITS
     and
    3.06
     –
    2.59
    ))=\
    2.38
    ﻂ
    2.25
    This
    2.23
    It
    2.22
    If
    2.17
    🤌
    2.14
     Viernes
    2.13
    🤘
    2.09
    Activations Density 0.097%

    No Known Activations