© 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. 39108
    Prev
    Next
    INDEX
    Explanations

    usual Slashdot

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

    The neuron strongly activates on numeric tokens that include decimal points (i.e. floating‐point 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
    zbęd
    -1.30
     "',
    -1.25
     "'";
    -1.21
     fatos
    -1.21
    `}
    -1.20
    peka
    -1.20
    ();)
    -1.18
    $.}
    -1.17
    過ぎる
    -1.16
    }
    -1.16
    POSITIVE LOGITS
    ti
    1.41
    0
    1.31
    ти
    1.27
    不
    1.26
    我
    1.24
    高
    1.23
     vs
    1.21
     had
    1.19
    人
    1.18
     advantages
    1.15
    Activations Density 0.095%

    No Known Activations