© 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. 34-GEMMASCOPE-RES-131K
    7. 116319
    Prev
    Next
    INDEX
    Explanations

    value, values, positive

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

    This neuron fires on the apostrophe-s suffix (the “’s” sequence) in the text.

    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
     incid
    -0.87
    athing
    -0.87
     calles
    -0.86
     PUBL
    -0.84
    stalgia
    -0.84
    moy
    -0.80
    ﻜ
    -0.80
     ressemble
    -0.79
     assass
    -0.79
    惮
    -0.79
    POSITIVE LOGITS
     value
    1.32
     values
    1.16
    value
    1.15
     Value
    0.94
     can
    0.86
     bulundu
    0.85
    cyclo
    0.85
     valore
    0.85
     Values
    0.83
     Wert
    0.83
    Activations Density 0.000%

    No Known Activations