© 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. 65137
    Prev
    Next
    INDEX
    Explanations

    hoped, wanted, planned, expected outcomes

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

    The neuron flags verbs that express a speaker’s mental stance—thinking, wanting, hoping, etc.

    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
     that
    -1.13
     estadía
    -0.89
     alcuni
    -0.89
     contribución
    -0.87
     ennek
    -0.85
     Discharge
    -0.84
    未満
    -0.84
     alcune
    -0.83
    
    -0.82
     издание
    -0.82
    POSITIVE LOGITS
     when
    1.19
     Originally
    1.11
     semula
    1.04
     them
    1.02
     possible
    1.00
    Originally
    0.99
     Despite
    0.95
     originalmente
    0.94
    MISSING
    0.93
     Sometimes
    0.93
    Activations Density 0.029%

    No Known Activations