© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44295
    Prev
    Next
    INDEX
    Explanations

    for the

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

    This neuron detects Razor view helper method calls with the “For” suffix (e.g. EditorFor, LabelFor, DisplayFor).

    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
     agricultura
    -1.45
    
    -1.41
     modifica
    -1.41
     telo
    -1.40
    睃
    -1.39
    ...»
    -1.38
     carica
    -1.37
     by
    -1.36
     identifica
    -1.35
     polie
    -1.34
    POSITIVE LOGITS
     hogy
    2.02
     что
    1.79
    2
    1.66
     že
    1.61
    1
    1.53
     that
    1.46
    3
    1.45
    9
    1.42
     mutta
    1.41
     że
    1.39
    Activations Density 0.002%

    No Known Activations