© 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. 112774
    Prev
    Next
    INDEX
    Explanations

    stor- prefix variations

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

    The neuron fires strongly on any token containing the substring “stor,” picking out occurrences of “stor” whether as a standalone piece or embedded in longer words.

    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
    逦
    -3.81
     adil
    -3.47
     内衣
    -3.44
     meras
    -3.36
     kitab
    -3.20
     aussit
    -3.19
    👹
    -3.14
     diki
    -3.11
    🍜
    -3.09
     portugu
    -3.08
    POSITIVE LOGITS
     {
    3.63
    {
    3.53
    0
    3.53
                    
    3.33
    9
    3.19
      
    3.17
    -
    3.11
              
    3.11
         
    3.08
     We
    3.02
    Activations Density 0.007%

    No Known Activations