© 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. 34-GEMMASCOPE-RES-131K
    7. 117152
    Prev
    Next
    INDEX
    Explanations

    technical or legal text

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

    This neuron activates on numeric tokens (integer literals and version 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_34/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
     häm
    -0.77
    Descripción
    -0.77
     خواهید
    -0.76
    organization
    -0.75
     kontroll
    -0.68
    นั้น
    -0.68
     Judah
    -0.67
    ազմ
    -0.67
     composición
    -0.67
    overlap
    -0.66
    POSITIVE LOGITS
     linear
    0.78
    råd
    0.71
     назначения
    0.70
    TAT
    0.69
     헤
    0.67
    حق
    0.67
     最後
    0.66
     Sligo
    0.65
     fuertemente
    0.64
    Ѧ
    0.64
    Activations Density 0.072%

    No Known Activations