© 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. 112787
    Prev
    Next
    INDEX
    Explanations

    Number or quantity references

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

    This neuron is essentially inactive—it never reliably fires on any specific token or pattern.

    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
    馓
    -2.86
    ࿆
    -2.56
     atractivos
    -2.56
     famosos
    -2.48
    CHREIB
    -2.44
     they
    -2.44
    웻
    -2.44
    M
    -2.44
     ของ
    -2.41
     wenn
    -2.39
    POSITIVE LOGITS
    an
    3.28
    ing
    3.02
    ان
    2.66
    er
    2.66
     ERSITY
    2.39
     After
    2.38
    Number
    2.33
    you
    2.30
    which
    2.27
    佯
    2.27
    Activations Density 0.006%

    No Known Activations